{"schema_version": 1, "checked_at": "2026-10-08T11:00:39Z", "refresh_hours": 1, "sources": [{"id": "arxiv-ai", "name": "arXiv · Artificial Intelligence", "topic": "Artificial intelligence", "url": "https://rss.arxiv.org/rss/cs.AI", "publisher": "arXiv", "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license", "status": "ok", "checked_at": "2026-10-08T11:00:32Z", "updated_at": "2026-10-08T11:00:32Z", "count": 447, "checksum": "1e6ae007326a420f7f0acd54f4ac8fe89baff9ec342b60cae2c211737115e033", "status_message": "Source checked successfully"}, {"id": "arxiv-cl", "name": "arXiv · Computation and Language", "topic": "Language models", "url": "https://rss.arxiv.org/rss/cs.CL", "publisher": "arXiv", "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license", "status": "ok", "checked_at": "2026-10-08T11:00:35Z", "updated_at": "2026-10-08T11:00:35Z", "count": 190, "checksum": "dc879f1365a486144ca76aab85a98217401ebec40ed409664d09b8833989a7fd", "status_message": "Source checked successfully"}, {"id": "cc", "name": "Creative Commons Open Source", "topic": "Open source", "url": "https://opensource.creativecommons.org/blog/feed.xml", "publisher": "Creative Commons Open Source", "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/", "status": "ok", "checked_at": "2026-10-08T11:00:39Z", "updated_at": "2026-10-08T11:00:39Z", "count": 50, "checksum": "f57676d2601d68dba4fdfdf8c3477365a9f50a1ec6d32a65d94877c8fd04ee27", "status_message": "Source checked successfully"}], "items": [{"id": "fe928d11ca43fa1b715d", "title": "Justice After Identity: Large Language Models and the View from Everywhere", "url": "https://arxiv.org/abs/2610.09053", "authors": "W. Russell Neuman", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "fe160aea59829126c1e7", "title": "Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents", "url": "https://arxiv.org/abs/2605.21347", "authors": "Akshay Manglik, Vijay S. Kalmath, Jason Qin, Apaar Shanker, Kaustubh Deshpande, Yash Maurya, Veronica Chatrath, Levi Lentz, Yuan Xue", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "fced489bde7609b7bff3", "title": "World Potential Model: Pretrained World Knowledge as Progress Potentials", "url": "https://arxiv.org/abs/2610.09560", "authors": "Jun Zhao, Jixin Tang, Yang Shu, Jinyang Wu, Yuyang Lu, Jingqi Tong, Hao Xu, Weifeng Ge, Qi Zhang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f97b508d001d2b6d62e1", "title": "Secure-CUA: Controlling Untrusted Influence in Computer-Use Agents", "url": "https://arxiv.org/abs/2610.09469", "authors": "Sarthak Choudhary, Mihai Christodorescu, Ashish Hooda, Somesh Jha, Tongxin Li, Damien Octeau", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f91a0a0f79139fd50eb8", "title": "Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions", "url": "https://arxiv.org/abs/2604.12138", "authors": "Aditya Agrawal, Alwarappan Nakkiran, Aman Singh Thakur, Alex Karlsson, Harsha Aduri", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f8690786fcb4f217f26b", "title": "Automatically Building and Updating a Knowledge Graph of MLIP Models", "url": "https://arxiv.org/abs/2610.09644", "authors": "Alexis Beer, Liudmyla Klochko, Mathieu d'Aquin", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f772918b44f1bd163cc7", "title": "CrisisFake: Benchmark Validity of AI-Generated Text Detection for Disaster Social Sensing", "url": "https://arxiv.org/abs/2609.35821", "authors": "Xiaoshan Zhou, Zaifu Zhan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f6d0df0193aa0786e7a8", "title": "Efficient Reasoning with Flow Language Models", "url": "https://arxiv.org/abs/2610.09416", "authors": "Hanru Bai, Faissal Izermine, Oscar Davis, T. Konstantin Rusch", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f483d67db498d7e335b8", "title": "Alice: A Large-Scale German Benchmark for Rubric-Based Multi-Dimensional Automatic Short Answer Scoring", "url": "https://arxiv.org/abs/2610.09661", "authors": "Zhifan Sun, Sebastian Gombert, Jannik Lossjew, Tobias Wyrwich, Berrit Katharina Czinczel, David Bednorz, Marcus Kubsch, Knut Neumann, Hendrik Drachsler", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f2973d7e01dc91aead4f", "title": "Why Software Engineering Is Indispensable in the Age of Coding Agents", "url": "https://arxiv.org/abs/2610.10226", "authors": "Alfonso Fuggetta", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f2858626d332df9fbd64", "title": "Persuasion Propagation: Does Persuasion Change AI Agent Behavior?", "url": "https://arxiv.org/abs/2602.00851", "authors": "Hyejun Jeong, Amir Houmansadr, Shlomo Zilberstein, Eugene Bagdasarian", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "f16914f03a4a24ab44d8", "title": "How Language Models Organize and Structure Moral Knowledge", "url": "https://arxiv.org/abs/2608.27402", "authors": "Orion Reblitz-Richardson", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Search & knowledge", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "eea1f685d8b8595e00fc", "title": "UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation", "url": "https://arxiv.org/abs/2610.09823", "authors": "Deyuan Liu, Yihao Hu, Jingxuan Zhang, Xingying Li, Jun Xie, Jiacheng Liu, Jungang Li, Yu Huang, Xuanyi Liu, Yue Ding, Zecheng Wang, Lei Zhao, Mingda Wang, Zhenglin Cheng, Peng Sun, Tao Lin", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ee9153b8e35e0b462ce3", "title": "Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation", "url": "https://arxiv.org/abs/2610.09209", "authors": "Thushara Manjari Naduvilakandy, Hyeju Jang, Mohammad Al Hasan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ed5f3b3646fed7b2c2f4", "title": "Autonomous Driving Research Requires a Community-Driven Data Paradigm", "url": "https://arxiv.org/abs/2610.08825", "authors": "Jinsu Yoo, Zanming Huang, Katie Z Luo, Zheda Mai, Qiyuan Wu, Bharath Hariharan, Mark Campbell, Wei-Lun Chao", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ec5a9ca9648cc3d0a2e0", "title": "CircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathies", "url": "https://arxiv.org/abs/2610.09643", "authors": "Gabriel Ocana-Santero, Marko Tvrdic", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "eb3cc17f89fa6c70db49", "title": "Finding the Right Balance: Relevance and Diversity in LLM Retrieval", "url": "https://arxiv.org/abs/2610.09412", "authors": "Guillaume Brouillette (Universit\\'e du Qu\\'ebec \\`a Trois-Rivi\\`eres, Trois-Rivi\\`eres, Canada), Faustin Kagabo (Universit\\'e du Qu\\'ebec \\`a Trois-Rivi\\`eres, Trois-Rivi\\`eres, Canada), Usef Faghihi (Universit\\'e du Qu\\'ebec \\`a Trois-Rivi\\`eres, Trois-Rivi\\`eres, Canada), Nadia Ghazzali (Universit\\'e du Qu\\'ebec \\`a Trois-Rivi\\`eres, Trois-Rivi\\`eres, Canada)", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ead272f05e79c8fd8884", "title": "RELATE: An Evaluation Framework for measuring Relational Orientation of Large Language Models", "url": "https://arxiv.org/abs/2610.09569", "authors": "Shivam Shukla, Jihye Kim, Shubham Gaur, Mahnaz Roshanaei, Magy Seif El-Nasr", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e7aa536b110d44a470d0", "title": "Adaptive Code Generation for Controlling Robots", "url": "https://arxiv.org/abs/2610.09588", "authors": "Justus Flerlage, Thorsten Wittkopp, Alexander Acker, Odej Kao", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e6bd77f43fe346bcf3f6", "title": "Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation", "url": "https://arxiv.org/abs/2605.31478", "authors": "Hui Wu, Xiaoyang Wang, Zhong Fan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Coding & development", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e68e1d7ebbe09b81353b", "title": "Dialect-Robust Speech Language Models with Synthetic Pseudo-Dialect Augmentation", "url": "https://arxiv.org/abs/2610.09321", "authors": "Shunsuke Mitsumori, Tomoya Mizumoto, Yusuke Fujita", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e5c16cb3d14b5523ce33", "title": "From Prompts to Trees: Effective LLM-Guided Tree Generation for Few-Shot Tabular Classification", "url": "https://arxiv.org/abs/2610.10227", "authors": "Yue Qiu, Zekang Du, Yiqun Diao, Bingsheng He, Qinbin Li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e451974ecae5e597875d", "title": "Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science", "url": "https://arxiv.org/abs/2610.09446", "authors": "Benjamin Wilcox, Dawei Gao, Pradeeban Kathiravelu, Douglas Causey, Kewei Sha, Yunhe Feng", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e41390f61ecbc35469b1", "title": "From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer Feedback", "url": "https://arxiv.org/abs/2610.09377", "authors": "Prabhath Chellingi, Raviraja G, Viraj Bagal", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e3f68bad0b5ea49c1842", "title": "OOM-RL II: Reality Is an Oracle, Not a Debugger Provenance-Constrained Diagnosis in Continually Evolving Agent-Engineered Systems", "url": "https://arxiv.org/abs/2610.10256", "authors": "Kun Liu, Liqun Chen", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e3e3b3e39d875ba9b213", "title": "Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs", "url": "https://arxiv.org/abs/2608.13368", "authors": "Dingzhan Nong, Zhihao Ren, Ziqi Li, Tim Lo", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e15c7d3de5e7f265cb89", "title": "DrugTargetWorld: A Synthetic Biobank for Training and Benchmarking AI Scientists", "url": "https://arxiv.org/abs/2610.09558", "authors": "Samuel Margolis, Paul Schmiedmayer, Alan Huang, Ethan Chen, Ishan Bhattacharjee, Atman Shah, Ben Viggiano, Fang Cao, Shriya Reddy, Roger Xia, Jack O'Sullivan, Daniel Katz, Matthew Wheeler, Euan Ashley, Bruna Gomes", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e05a03b0413aef1b70d3", "title": "Breaking the Space Barrier and its Application to Language Model Inference", "url": "https://arxiv.org/abs/2610.09139", "authors": "Arip Asadulaev", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e019b35d051a20865949", "title": "Adaptive Workflow Intelligence: A Cognitive Architecture for Context-Driven Enterprise Automation", "url": "https://arxiv.org/abs/2610.08793", "authors": "Sreedevi Pandiyath Viswambaran", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e00db7c212beb635f3f1", "title": "FREIDA: A Framework for developing quantitative agent based models based on qualitative expert knowledge", "url": "https://arxiv.org/abs/2308.00505", "authors": "Frederike Oetker, Vittorio Nespeca, Rick Quax", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "df6e744578f407e1dfa4", "title": "QuanLing: Cross-Branch Validation of Language Distance Quantification on Western Romance", "url": "https://arxiv.org/abs/2610.08851", "authors": "Yiping Bai", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "dd28e1bf3dc65d80c5f2", "title": "Evaluating Trajectory Features for Routing Final-Layer Attention", "url": "https://arxiv.org/abs/2610.09272", "authors": "Yupeng Yao", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "dc899dc4881918fb74ab", "title": "Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents", "url": "https://arxiv.org/abs/2610.09856", "authors": "Wenjie Liao, Liangjie Zhao, Zehong Cao", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "dc23fb37627ab187fc56", "title": "RACER: Reflective Agent Coupling Query Interpretation and Tool-Based Retrieval for Frame Selection in Long Video Understanding", "url": "https://arxiv.org/abs/2610.08954", "authors": "Yiyang Huang, Yitian Zhang, Yizhou Wang, Jianglin Lu, Qihua Dong, Hailing Wang, Huimin Zeng, Mingyuan Zhang, Yun Fu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "db759386f9c3a80729fc", "title": "Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models", "url": "https://arxiv.org/abs/2610.08966", "authors": "Xingang Guo, Jing Gu, Brian Jang, Renxiong Wang, Utkarsh Tyagi, Daniel Quigley, Steven Li, David Yan, Daniel Yue Zhang, Darvin Yi, Forrest Huang, HiJae Kim, Tianyi Zhang, Jared Lichtarge, Jihua Huang, Le Xue, Manan Tomar, Qiuyi Richard Zhang, Ruofei Yu, Seth Neel, Yaning Hu, Marcella Valentine, Xinzhe Jiang, Daniel Evans, Chenguang Wang, Dustin Tran, Tong Zhao, Yinfei Yang, Yunzhong He", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "db133fd11bb78f0e7902", "title": "Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning", "url": "https://arxiv.org/abs/2610.10358", "authors": "Junkai Chen, Yuhao He, Qianshan Wei, Junxiang You, Jingwen Shao, Junkai Lin, Zhongkai Yue, Xiaotian Ye, Zhengbo Jiao, Jiali Cheng, Zhijie Deng, Kening Zheng, Ruiqi Liu, Hadi Amiri, Yi Yu, Zhenan Sun, Qi Li, Ka-Ho Chow, Sijia Liu, Liang Wang, Jiaqi Li, Shu Wu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "da8f097911d87d862371", "title": "Constraint Tree Exploration for Learning from Language Feedback", "url": "https://arxiv.org/abs/2610.09107", "authors": "Shaoang Li, Daniel R. Jiang, Jian Li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "da55870f0e4bea289bf1", "title": "VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding", "url": "https://arxiv.org/abs/2610.10183", "authors": "Yongchao Xu, Bowen Ye, Jiefeng Gan, Junkai Ma, Wenzhao Li, Sen Tao, Yi Wei, Jiawei Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d9b79c9e0b99ef77de54", "title": "BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech", "url": "https://arxiv.org/abs/2610.09464", "authors": "Rohit Kumar Sen, Anik Chowdhury", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d90a8e0869dee55cdcc0", "title": "SciExam for ENSO: Can AI Agents Build Climate Models?", "url": "https://arxiv.org/abs/2610.10513", "authors": "Yinling Zhang, Langchen Liu, Dongbin Xiu, Xueyan Zou, Xu Kuang, Mengdi Wang, Shilong Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d761228baa4bd20e28fb", "title": "Tokka-Bench: Evaluating Tokenizers Across 100 Natural and 20 Programming Languages", "url": "https://arxiv.org/abs/2610.08794", "authors": "Ben Gubler", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d757d2588a884e6580e2", "title": "PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs", "url": "https://arxiv.org/abs/2610.10455", "authors": "Linghao Meng, Feng He, Xuan Yang, Junyuan Mao, Pinze Ren, Deqing Mu, Hesen Yang, Qiankun Li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d622008d65172db695eb", "title": "APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation", "url": "https://arxiv.org/abs/2605.09492", "authors": "Tianyu Zheng, Hong Wu, Jiaji Zhong", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d57cb6923dde9050eda7", "title": "WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites", "url": "https://arxiv.org/abs/2610.03036", "authors": "Jiangang Han", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d1e3741c6eebbe042e94", "title": "Large-scale Repository Engineering via Agent-Native Reusable Code Primitives", "url": "https://arxiv.org/abs/2610.09079", "authors": "Haibo Jin, Peng Kuang, Xucheng Yu, Jerry Wang, Dehao Wu, Haohan Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Agents & automation", "Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d13608129bc32df64d84", "title": "Multimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding", "url": "https://arxiv.org/abs/2610.09355", "authors": "Parastoo Azizeddin, Omid Sharafi, Maryam M. Shanechi", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d11a86a2666a53394e1d", "title": "Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification", "url": "https://arxiv.org/abs/2610.09486", "authors": "Minu Kim, Jihwan Lee, David R. Mortensen, Shrikanth Narayanan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d10017faab1070b01d93", "title": "NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning", "url": "https://arxiv.org/abs/2602.20119", "authors": "Jiahui Fu, Junyu Nan, Lingfeng Sun, Hongyu Li, Jianing Qian, Benjamin Yang, Yilun Du, Jennifer L. Barry, Kris Kitani, George Konidaris", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d0ffa45556f4d37cef78", "title": "Benchmarking Generative Models for Near-Surface Data Assimilation on Real Station Observations", "url": "https://arxiv.org/abs/2610.00728", "authors": "Ruizhe Huang, Qidong Yang, Jonathan Giezendanner, Sherrie Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d0f8ebef91a045e3b96b", "title": "Contextualization of Third-Party Cloud Security Findings", "url": "https://arxiv.org/abs/2610.08895", "authors": "Leon Goldberg, Gal Engelberg", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "d0976f44b3b7a8437cfa", "title": "Decoupled Multi-Agent Orchestration", "url": "https://arxiv.org/abs/2610.07556", "authors": "Xinle Wu, Yao Lu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "cfdd0bbc348aa2577097", "title": "KGATE : a Knowledge Graph Embedding Training Environment", "url": "https://arxiv.org/abs/2610.09927", "authors": "Benjamin Loire, Galadriel Bri\\`ere, C\\'elia Brahimi, Antoine Toffano, Ana\\\"is Baudot", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "cd1f4d3caad55133a784", "title": "SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements", "url": "https://arxiv.org/abs/2607.27409", "authors": "Pengyu Xue, He Yang Yuan, Xin Wang, Junkai Chen, Haonan Zhang, Boyuan Chen, Zishuo Ding, Zhenhao Li, Weiyi Shang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "cc3769f520a9021e2391", "title": "DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis", "url": "https://arxiv.org/abs/2610.09374", "authors": "Yizhi Song, Hang Ni, Weijia Zhang, Hao Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c9fa27356ba6c3feb0cd", "title": "Diagnosing and Improving Probabilistic Reasoning in Large Language Models", "url": "https://arxiv.org/abs/2609.38005", "authors": "Huaman Sun, Dingcheng Wang, Jason Hartline, Jessica Hullman", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c9d54e556f48302c411d", "title": "When the Governor Becomes the Disturbance: Control-Generated Disturbance and Cost-Aware Backoff in Governed Tool-Using Agents", "url": "https://arxiv.org/abs/2610.09037", "authors": "Veronique Ziegler", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c905ab227fe6d4ef35fa", "title": "A Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video", "url": "https://arxiv.org/abs/2610.09217", "authors": "Wenqi Li, Mindi Ruan, Chuanbo Hu, Shuo Wang, Xin Li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c6d5827c4d3857b329d0", "title": "WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents", "url": "https://arxiv.org/abs/2606.02908", "authors": "Hengrui Gu, Xiaotian Han, Kaixiong Zhou", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c6459dab273b47fe48df", "title": "Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models", "url": "https://arxiv.org/abs/2610.06387", "authors": "Joe Dwyer", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c5ff7aa2dd9bad6fc753", "title": "From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents", "url": "https://arxiv.org/abs/2610.09973", "authors": "Juanyang Xu, Zheng Wang, Xingyu Zhao, Siddartha Khastgir, Andi Zhang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c4922e5d02591574f1fc", "title": "Coding-Agent Benchmarks Should Match Their Users' Task Flows", "url": "https://arxiv.org/abs/2610.09633", "authors": "Igor Slinko, Yaroslav Golubev, Sergey Titov", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Agents & automation", "Coding & development", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c40bbf9289cd087a86ab", "title": "ReToken: Improving Long-Context VLMs with Visual Retrieval Token", "url": "https://arxiv.org/abs/2607.28627", "authors": "Yao Xiao, Reuben Tan, Zhen Zhu, Yuqun Wu, Jianfeng Gao, Derek Hoiem", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c3a1c929687d587a62ec", "title": "Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution", "url": "https://arxiv.org/abs/2610.09772", "authors": "Masaaki Nakatsu (AO, Inc. / OrbLabs AG), Reno Wang (AO, Inc.)", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c39c00dca43889476462", "title": "LLM Persuasion Is in the Eye of the Evaluation", "url": "https://arxiv.org/abs/2610.10232", "authors": "Kamile Dementaviciute, Julija Vaitonyte, Tijl De Bie", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c3582e5fb8e6cbe88584", "title": "Structured pre-generation elicitation versus single-shot prompting in AI-assisted enterprise decision-making: a randomised online experiment", "url": "https://arxiv.org/abs/2610.09593", "authors": "William Scott-Jackson", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c23f9ff58a5cc819c9dd", "title": "Surprisal Theory is Tautological (without Rational Grounding)", "url": "https://arxiv.org/abs/2607.21574", "authors": "Ryan Cotterell", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "c15e62e8799c6409baca", "title": "GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function Reasoning", "url": "https://arxiv.org/abs/2610.10201", "authors": "Jingyao Zhang, Yun Li, Lu Han", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "bfff0672136878ccce10", "title": "Towards Explaining Query Expansion Performance in Information Retrieval", "url": "https://arxiv.org/abs/2610.09724", "authors": "Sourav Saha, Aditya Dutta, Soumajit Pramanik, Mandar Mitra", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "bf454e7c9de0f2b60d98", "title": "Do Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency", "url": "https://arxiv.org/abs/2610.09205", "authors": "M. Moein Esfahani, Sepehr Salem, Mohammed Alser, Vince Calhoun", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "be9eea4b31c98cf0509d", "title": "How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis", "url": "https://arxiv.org/abs/2610.09000", "authors": "Muhammad Zeeshan Karamat, Christiana Chamon Garcia", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "bdec117830c4b1e723f3", "title": "CARE: Certifying Acceleration for Vision-Language-Action Inference", "url": "https://arxiv.org/abs/2610.08917", "authors": "Rui Liu, Tong Zheng, Jindong Gu, Zhipeng Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "bc2d1a9301c185c8cc2a", "title": "Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents", "url": "https://arxiv.org/abs/2610.10179", "authors": "Wenyu Huang, Xinyu Hou, Pavlos Vougiouklis, Ruofei Lai, Jeff Z. Pan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "bb5b4da7666f8ea1c18d", "title": "Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents", "url": "https://arxiv.org/abs/2610.08928", "authors": "Nikolaos Kekatos, Dimitrios Nikou, Anastasios Temperekidis, Alexios Lekidis, Nikolaos Kolokotronis, Panagiotis Katsaros, Stylianos Basagiannis", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ba2e21fa3912c7de67e3", "title": "EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory", "url": "https://arxiv.org/abs/2610.10533", "authors": "Hongru Cai, Ran Wei, Wenjie Wang, Chengfa Wu, Ning Song, Yongqi Li, Wenjie Li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b9f783daa190b57a2d51", "title": "Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs", "url": "https://arxiv.org/abs/2610.09581", "authors": "Taehyeon Yun, Dongho Kim, Geonwoo Kim, Juyoung Seo, Minseok Hur, Moohong Min", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b92b08173531b188d431", "title": "RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement", "url": "https://arxiv.org/abs/2610.09426", "authors": "Renxiong Wang, Darvin Yi, Abril Herrlein, Anas Mahmoud, Advait Gosai, Lisiman Hua, MohammadHossein Rezaei, Xingang Guo, Anisha Gunjal, Utkarsh Tyagi, David J. Lee, Minglai Yang, Haris Riaz, Chenguang Wang, Huaxiu Yao, Daniel Yue Zhang, Aakash Sabharwal, Tong Zhao, Yunzhong He", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b815df87a08170ac0dce", "title": "MIMESIS: Learning User Simulators as Training Environments for Interactive Agents", "url": "https://arxiv.org/abs/2610.09484", "authors": "Hoang Phan, Dat Huynh, Andrey Zhmoginov, Qi Zeng, Wancen Mu, Yue Cao, Shengjie Bi, Yun He, Changdae Oh, Deren Lei", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b643bf3f67891a370475", "title": "Towards Direct Evaluation of Harness Optimizers via Priority Ranking", "url": "https://arxiv.org/abs/2605.22505", "authors": "Kai Tzu-iunn Ong, Minseok Kang, Dongwook Choi, Junhee Cho, Seungju Kim, Seungwon Lim, Geunha Jang, Minwoo Oh, Bogyung Jeong, Sunghwan Kim, Taeyoon Kwon, Jihye Han, Juyoung Wy, Jinyoung Yeo", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b5a9325d774561958522", "title": "TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity", "url": "https://arxiv.org/abs/2610.10374", "authors": "Chengwei Shi, Yunnong Chen, Tingting Zhou, Qiang Lu, Shiyu Yue, Xinyuan Hu, Jianfang Ru, Liuqing Chen", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Coding & development", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b510f96ba6d0a941e94f", "title": "PAIR: Bridging Perception and Action in Vision-Language-Action Models", "url": "https://arxiv.org/abs/2610.09016", "authors": "Kaixi Feng, Guoheng Sun, Ang li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b45120f344d18607f0d1", "title": "Training Advisors for LLM Agents from Task Outcomes", "url": "https://arxiv.org/abs/2610.09858", "authors": "Sergei Polezhaev, Barys Liskavets, Ori Press, Alexander Golubev", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b36dc5a3d1ab317a064d", "title": "SearchWorld: Spatial Value-Grounded Imagination for UAV Object Search via World Models", "url": "https://arxiv.org/abs/2610.09335", "authors": "Yatai Ji, Zhengqiu Zhu, Yong Zhao, Yue Hu, Fanglong Yao, Chen Gao, Pengfei Zhu, Quanjun Yin", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b2682c74a7a4a1cd2e7a", "title": "OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems", "url": "https://arxiv.org/abs/2604.11477", "authors": "Kun Liu, Liqun Chen", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b1aaf5458b2c3df36e7b", "title": "Cross-Agent Learning Signals Enable Coordinated Role-Decomposed LLM Training", "url": "https://arxiv.org/abs/2606.10684", "authors": "Jaewan Park, Solbee Cho, Jay-Yoon Lee", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b10a2d8a4830a61add16", "title": "Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models", "url": "https://arxiv.org/abs/2610.09496", "authors": "Jiho Lee, Jeongeun Park, Heayoun Choi, Taekyung Kim, Eunwoo Kim", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "b09c1f832ddbe698ea02", "title": "A Survey of Secure Retrieval-Augmented Generation", "url": "https://arxiv.org/abs/2604.08304", "authors": "Yuming Xu, Mingtao Zhang, Zhuohan Ge, Haoyang Li, Nicole Hu, Yongqi Zhang, Zhiyuan Wen, Jason Chen Zhang, Qing Li, Lei Chen", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "aef4ce03e54c90468022", "title": "Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Models", "url": "https://arxiv.org/abs/2610.10405", "authors": "Maverick Morales, Tom\\'a\\v{s} Dominik, Vermut Gao, Katrina Shirey, Paulius Rimkevi\\v{c}ius, Aaron Schurger, Uri Maoz", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "aec907937d5cc279e98a", "title": "CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use", "url": "https://arxiv.org/abs/2610.09127", "authors": "Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov, Albert Garifullin, Oleg Pavlov, Soslan Kabisov, Vladimir Frolov, Anton Konushin, Andrey Kuznetsov, Dmitrii Zhemchuzhnikov", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ae99a87ed08b41cb2d16", "title": "Demo: Vision-Language Model-Guided Online Calibration of an Electromagnetic Digital Twin", "url": "https://arxiv.org/abs/2610.07081", "authors": "Zerui Kang, Yishen Lim, Zhouyou Gu, Seungnyun Kim, Seung-Woo Ko, Tony Q. S. Quek, Jihong Park", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ae7a6e0399a0e16d4b3b", "title": "Attention at Rest Stays at Rest: Breaking Visual Inertia to Mitigate Relation Hallucinations", "url": "https://arxiv.org/abs/2604.01989", "authors": "Boyang Gong, Yu Zheng, Fanye Kong, Jie Zhou, Jiwen Lu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ae470677c12c7906a119", "title": "What Does Multi-Agent Debate Actually Change?", "url": "https://arxiv.org/abs/2609.08016", "authors": "Chen Qian", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "acb278ff953696127f66", "title": "Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems", "url": "https://arxiv.org/abs/2610.08901", "authors": "Tunyu Zhang, Zihao Zhao, Yusong Zhao, Haizhou Shi, Zhuohang Li, Haoxian Chen, Hao Wang, Dimitris N. Metaxas", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ac4f7fe179b30581cf3f", "title": "Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR", "url": "https://arxiv.org/abs/2610.09934", "authors": "Ibrahim Almajai", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "ac050066e224a6172fb7", "title": "Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time", "url": "https://arxiv.org/abs/2609.32701", "authors": "Jacob Dineen, Silei Ren, Muhao Chen, Dan Roth, Ben Zhou", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "aad4b400af139015585f", "title": "Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving", "url": "https://arxiv.org/abs/2605.00556", "authors": "Ashwin George, Lucas Elbert Suryana, Lorenzo Flipse, Bart van Arem, David A. Abbink, Simeon Craig Calvert, Luciano Cavalcante Siebert, Arkady Zgonnikov", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a8e723f434e0eca8d3d4", "title": "SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions", "url": "https://arxiv.org/abs/2610.10407", "authors": "Yizhen Xie, Mengyang Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a8693e437eb2f7f44124", "title": "Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs", "url": "https://arxiv.org/abs/2610.09033", "authors": "Pavan Maddula", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a8067fb5bf52bedc7bce", "title": "Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks", "url": "https://arxiv.org/abs/2610.09870", "authors": "Bernardo A. C. Pereira, Marcos Carvalho, Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci, Andreas Gavrielides, Johann M. Marquez-Barja, Daniel F. Macedo", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a7c433f27747d4d5be53", "title": "Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coordination", "url": "https://arxiv.org/abs/2609.14767", "authors": "Burak Agachan, Max van Duijn, Amirhossein Zohrehvand", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a73625cce6aded6f8dfd", "title": "Doc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Induction", "url": "https://arxiv.org/abs/2602.04892", "authors": "Shihao Xia, Mengting He, Haomin Jia, Xinyan Zhao, Linhai Song", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a64f006c8bc1d6573ae4", "title": "Reliability of LLM Judges for Evaluating Entity Alignment", "url": "https://arxiv.org/abs/2610.09554", "authors": "Vaibhava Lakshmi Ravideshik, Mayank Kejriwal", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a356871e178300104162", "title": "Learning to Report Unsafe Tasks in a Multi-Agent Game", "url": "https://arxiv.org/abs/2610.09002", "authors": "Avyay M. Casheekar, Hariganesh Tangirala", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "a13bbb297eb54c7ef48c", "title": "AgentTime: Can Agents Estimate and Control Their Own Runtime?", "url": "https://arxiv.org/abs/2610.09944", "authors": "Michael Ofengenden, Maksym Andriushchenko", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "9e0c6401d05befd31408", "title": "Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization", "url": "https://arxiv.org/abs/2610.08969", "authors": "Gustavo Sutter, Alejandro Comas-Leon, David Holzm\\\"uller, Hao Wang, Luis Ricardez-Sandoval, Pascal Poupart, Agustinus Kristiadi", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "9ca5f78df499921e401d", "title": "What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?", "url": "https://arxiv.org/abs/2610.09700", "authors": "Nikos Giakoumoglou, Paschalis Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "9a8c130e4869e39e3eaf", "title": "Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents", "url": "https://arxiv.org/abs/2605.12894", "authors": "Harshita Chopra, Kshitish Ghate, Aylin Caliskan, Tadayoshi Kohno, Chirag Shah, Natasha Jaques", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "986cc5828afb886bc4a2", "title": "Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network", "url": "https://arxiv.org/abs/2610.09034", "authors": "Brandon Ho, Nikola Rogers, Seung-Kyum Choi", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "977ffc6527622a8f41ba", "title": "Training Language Models To Be Coherent Decision-Makers", "url": "https://arxiv.org/abs/2610.09164", "authors": "Khurram Yamin, Xavier Fernandes, Paul Koch, Bryan Wilder, Eric Horvitz", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "962f1ae61a67e236c364", "title": "AI Safety Considerations for Agents With Limited Time to Act", "url": "https://arxiv.org/abs/2610.10285", "authors": "Leo Zeitler, Jack Richings, Victoria Nockles", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "95699d5f1fe60a15639e", "title": "SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models", "url": "https://arxiv.org/abs/2610.09600", "authors": "Miao Yu, Hao Huang, Lu Yuan, Yunpeng Li, Kun Wang, Zuming Jiang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "9363228829aa963114bb", "title": "Collective Behavior of AI Agents: the Case of Moltbook", "url": "https://arxiv.org/abs/2602.09270", "authors": "Giordano De Marzo, Andres L. Marin, David Garcia", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "92a25ddc43940295a637", "title": "From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs", "url": "https://arxiv.org/abs/2610.10066", "authors": "Zijian Chen, Zhengyu Chen, Bohan Liang, Lirong Deng, Yushuo Zheng, Yanwei Jiang, Qi Jia, Kaiwei Zhang, Wenjun Zhang, Guangtao Zhai", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Coding & development", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "90b3146cbe4575a7fb5a", "title": "SpikingVLA: Asynchronous Spiking Vision-Language-Action Models", "url": "https://arxiv.org/abs/2610.09710", "authors": "Jingya Wang, Dehao Zhang, Shuai Wang, Malu Zhang, Yang Yang, Haizhou Li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8f9929ef7ffe5612dd3b", "title": "Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models", "url": "https://arxiv.org/abs/2605.10971", "authors": "Hanhan Zhou, Shamik Roy, Rashmi Gangadharaiah", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8e27b3b86b1fd54a7f12", "title": "RegNetAgents: A Multi-Agent Framework for Cross-Network Regulatory Driver Identification in Cancer Genomics", "url": "https://arxiv.org/abs/2607.14097", "authors": "Jose A. Bird", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8bfe7c10e4711d2e42f1", "title": "Ream: Unfolding Mutual Awareness in Human-Agent Workspaces", "url": "https://arxiv.org/abs/2610.09497", "authors": "Peiling Jiang, Sangho Suh, Varsha Kishore, Jonathan Bragg, Haijun Xia, Pao Siangliulue, Daniel S. Weld, Amy X. Zhang, Joseph Chee Chang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8b50099f7389c9f0beb1", "title": "An AI-assisted conditioning and geological interpretation workflow for usage in implicit geological modeling", "url": "https://arxiv.org/abs/2610.09871", "authors": "Stefan Carpentier, Jan Diederik van Wees, Eva de Boever, Jan Niederau, Camille Chapeland, Suzanne Atkins, Boris Boullenger, Jens Wollenweber", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8b28846018517afbb7e5", "title": "sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak", "url": "https://arxiv.org/abs/2610.09152", "authors": "Marek \\v{S}uppa, Ivan Vykopal, Andrej Ridzik, Kristi\\'an Sopkovi\\v{c}, Nat\\'alia K\\v{n}a\\v{z}ekov\\'a, Jaroslav Kop\\v{c}an, Miroslav Bl\\v{s}t\\'ak, Vikt\\'oria Ondrejov\\'a, Daniel Hl\\'adek, Michal Gregor, Martin Tamajka, Mari\\'an \\v{S}imko", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8a98abb83d63731375f5", "title": "Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models", "url": "https://arxiv.org/abs/2610.10526", "authors": "Mikey Watts (Independent Researcher), Yuchen Cui (University of California, Los Angeles)", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8a39b26a2e57f11c2121", "title": "NL2Hull: A Natural Language-Driven Constrained Ship Design Decision Framework", "url": "https://arxiv.org/abs/2610.09896", "authors": "Wenhua Huo, Fenglei Han, Wangyuan Zhao, Jialin Wu, Jiayi Han", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8a20f48fc4c0f8f9aaaf", "title": "Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay", "url": "https://arxiv.org/abs/2605.19352", "authors": "Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa, Satya Sai Srinath Namburi, Tanmoy Chakraborty, Bapi S. Raju, Manish Gupta", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8893bf9c9541d2f3e4bc", "title": "Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented Languages", "url": "https://arxiv.org/abs/2610.09467", "authors": "Muhammad Huzaifah, Yu Pan, Zachary Yeo, Ningjie Bai, Guangzhao Yang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "889192a8a3f8483898d5", "title": "TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning", "url": "https://arxiv.org/abs/2605.07943", "authors": "Giacomo Spigler", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8815690363c10f8118f9", "title": "Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents", "url": "https://arxiv.org/abs/2610.08993", "authors": "Jiamu Bai, Lizhu Zhang, Xin Yu, Yanhong Wu, Zellux Wang, Serena Li, Weiwei Li, Zhuokai Zhao, Lingzhou Xue, Kiwan Maeng, Xiangjun Fan, Bo Peng", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "87d5ac9ec650b9b35594", "title": "Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training", "url": "https://arxiv.org/abs/2606.06539", "authors": "Yucheng Chen", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8777e4bbe8c246972478", "title": "TACTICS: Taxonomy-Aware Intelligent Corpus Sampling for Machine Translation", "url": "https://arxiv.org/abs/2609.17956", "authors": "Prasanth Bathala, Anubhav Shrimal, Sukhdeep Singh Kharbanda, Pradyumna Lanka, Rohit Dhaipule", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "85f98a0e6a1d5285b372", "title": "Talking with Language Models", "url": "https://arxiv.org/abs/2610.09064", "authors": "James Ravi Kirkpatrick, Alexandru Radulescu, Rachel Katharine Sterken", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "848ac8792a663f889ccb", "title": "ArapaiSecure: An Autonomous AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts", "url": "https://arxiv.org/abs/2606.17555", "authors": "Joseph Walusimbi, Joshua Benjamin Ssentongo", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "845eabed530fb40f5abb", "title": "EEG and Eye-Tracking Evidence That AI Disclosure Shapes Face Evaluation", "url": "https://arxiv.org/abs/2610.10182", "authors": "Teodora Mitrevska, Luise Donat, Andreas Butz, Thomas Kosch, Abdallah El Ali, Francesco Chiossi", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8438b2b38b4a702bcf4b", "title": "Node-level Graph Neural Architecture Search Framework", "url": "https://arxiv.org/abs/2610.09297", "authors": "Lintao Yanga, Sirui Lia, Yaqing Wang, Pietro Li\\`o, Xu Shen, Baisong Liu, Chengbin Peng", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "83e2f18d4e8cf0f25867", "title": "COMPASS: Finding Where Reasoning Lives in Language Models", "url": "https://arxiv.org/abs/2610.07469", "authors": "Pratyay Dutta, Kowshik Thopalli, Vivek Narayanaswamy", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "8328d66044226114c9f6", "title": "HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews", "url": "https://arxiv.org/abs/2609.03580", "authors": "Tzu-Ling Lin, Dong-Ting Yao, Teng-Fang Hsiao, Wei-Chih Chen, Hong-Han Shuai", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "82c1305bb043298cfee7", "title": "Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents", "url": "https://arxiv.org/abs/2608.12851", "authors": "Xutao Mao, Liangjie Zhao, Xiang Zheng, Cong Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "80ea796abc4612606f5e", "title": "OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models", "url": "https://arxiv.org/abs/2610.09346", "authors": "Wenjun Wang, Heng Li, Yanggan Gu, Hongxia Yang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "80dfd5e8087e3f2b0c71", "title": "We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents", "url": "https://arxiv.org/abs/2610.09243", "authors": "Kefan Liu, Fengning Ou, Yelin Luo, Jingdi Lei", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "806b0adcad9a1f2aac19", "title": "Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn Search Agents", "url": "https://arxiv.org/abs/2607.06223", "authors": "Yijun Zhang, Fan Xu, Jiaxin Ding, Yule Xie, Xin Ding, Haoxiang Zhang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7f70a427627278681a8b", "title": "When Does a Spoken Agent Have Enough Evidence to Act? The PACT-SLM Contract Test", "url": "https://arxiv.org/abs/2609.38232", "authors": "Mengzhe Geng", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7e4464dd53abba009fea", "title": "Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators", "url": "https://arxiv.org/abs/2602.22647", "authors": "Zhengyang Su, Isay Katsman, Yueqi Wang, Ruining He, Lukasz Heldt, Raghunandan Keshavan, Shao-Chuan Wang, Xinyang Yi, Mingyan Gao, Onkar Dalal, Lichan Hong, Ed Chi, Ningren Han", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7e2b39abdb0c1bb4d922", "title": "Bridging Natural Language and Interactive What-If Interfaces via LLM-Generated Declarative Specifications", "url": "https://arxiv.org/abs/2604.07652", "authors": "Sneha Gathani, Sirui Zeng, Diya Patel, Ryan Rossi, Dan Marshall, Cagatay Demiralp, Steven Drucker, Zhicheng Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7d7083e5e533ece38ded", "title": "The AI Evaluation Ecosystem", "url": "https://arxiv.org/abs/2610.09296", "authors": "Yash Dave, Sang T. Truong, Serena Wang, Sanmi Koyejo", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7caa79e0d5fd9d33d3f0", "title": "RoboQuest: Generalist Physical Agents that Search, Inspect and Test", "url": "https://arxiv.org/abs/2610.10388", "authors": "Liu Renhang, Navonil Majumder, Tej Deep Pala, Soujanya Poria", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7c7c0eb56ee6166b8f7d", "title": "ED3R: Energy-Aware Distributed Disaster Detection via Cooperative Agents in Robotic Systems", "url": "https://arxiv.org/abs/2606.17739", "authors": "Lina Magoula, Nikolaos Koursioumpas, Nancy Alonistioti, Ramin Khalili", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7ac643a07de298adee18", "title": "APE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation", "url": "https://arxiv.org/abs/2505.19912", "authors": "Javier Mar\\'in", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7a2ca7b425ff8885a2fa", "title": "SpecGuard: Proving a Task Is Broken Before the Agent Cheats", "url": "https://arxiv.org/abs/2610.09159", "authors": "Param Biyani, Krishnamurthy Dvijotham", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7a0af9b042ee5581e9e8", "title": "Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning", "url": "https://arxiv.org/abs/2610.09607", "authors": "HyeonSeok Lim, SeungWoo Song, Inho Won, Hoyun Song, Jihyo Kim, KyungTae Lim", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "78a338993ea0b81f1734", "title": "CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution", "url": "https://arxiv.org/abs/2610.10426", "authors": "Jixuan Chen, Jiaxin Zhang, Qinyuan Ye, Yada Pruksachatkun, Haoxiang Zhang, Jingming Zhuo, Yifan Zhang, Yutong Dai, Juntao Tan, Xiangyu Peng, Silvio Savarese, Zeyuan Chen, Lianhui Qin, Chien-Sheng Wu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7859f6379c715a5d33e1", "title": "APEX: Active Protection at Execution Boundaries for LLM Agents", "url": "https://arxiv.org/abs/2610.06966", "authors": "Xinran Zheng, Xin Fan Guo, Zhiqiang Hao, Fan Yang, Xingzhi Qian, Jiawei Du, Jinfeng Xu, Zheng Xing, Shuo Yang, Xingjun Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "784b494af957644eda44", "title": "VIA: Visual Interface Agent for Robot Control", "url": "https://arxiv.org/abs/2607.11119", "authors": "Hengyuan Hu, Jensen Gao, Priya Sundaresan, Satvik Sharma, Jeannette Bohg, Dorsa Sadigh", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "76a874054c3560551487", "title": "Beyond Risk Prediction: Evidence Grounding and Psychosocial Factor Verification for Explainable Suicide Risk Assessment", "url": "https://arxiv.org/abs/2610.08842", "authors": "Tianle Hu, Chen Peng, Yi-Hsin Tsai, Takshing Andy Tung, Bingyang Sun, Yenjou Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7574fb870f52f1fe070d", "title": "The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets in Large Language Models", "url": "https://arxiv.org/abs/2610.10049", "authors": "Obada Kraishan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "745fa2299f05a01c5f7a", "title": "Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models", "url": "https://arxiv.org/abs/2610.10506", "authors": "Daniel Robert Kling Alexander, Catherine Louise Kling", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "7204e9059a27ad917d49", "title": "From Probabilities to Decisions: Search and Multi-Teacher Distillation with Jev", "url": "https://arxiv.org/abs/2610.09188", "authors": "Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "71e29a44e4f752e1226d", "title": "Agent Plasticity: Measuring Self-Improvement Through Experience", "url": "https://arxiv.org/abs/2610.08902", "authors": "Harman Singh, Anton Bakhtin, Rulin Shao, Gabriel Synnaeve, Ilia Kulikov, Rob Fergus, Sanjeev Arora, Kurt Keutzer, Jason Weston, Anuj Mahajan, Anirudh Goyal", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "713a684399905483b3bd", "title": "Efficient Best-of-N policy evaluation for inference-time alignment", "url": "https://arxiv.org/abs/2610.09250", "authors": "Jonas Schweisthal, Yuxin Wang, Athiya Deviyani, Stefan Feuerriegel, Dennis Frauen", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6f4d10392585cdacef3d", "title": "Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning", "url": "https://arxiv.org/abs/2610.08894", "authors": "Ryan C. Barron", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6f0264bfc79eb0ee5f47", "title": "GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents", "url": "https://arxiv.org/abs/2610.08959", "authors": "Bohan Lin, Liyi Chen, Zhuoning Guo, Muyang Li, Qimeng Wang, Yan Gao, Yao Hu, Yudong Zhang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6e97ead39530ea18635a", "title": "From Expert-Guided Proof Search to Automated Open-Problem Solving", "url": "https://arxiv.org/abs/2610.09769", "authors": "Adri\\'an Z\\'ame\\v{c}n\\'ik, Mat\\v{e}j Kripner, Martin Kouteck\\'y, Martin Balko, Jan Greb\\'ik, Pavel Hub\\'a\\v{c}ek, Robert \\v{S}\\'amal, V\\'aclav Rozho\\v{n}", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6e87228c64a8ec80ea99", "title": "A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents", "url": "https://arxiv.org/abs/2610.10468", "authors": "Ali Asaria, Deep Gandhi, Tony Salomone", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6bdc72a9f50338f45474", "title": "Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models", "url": "https://arxiv.org/abs/2610.10508", "authors": "Amanda Myntti, Jenna Kanerva, Veronika Laippala, Filip Ginter", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6bbf7975bcb0753e786a", "title": "When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs", "url": "https://arxiv.org/abs/2607.21445", "authors": "Anna Mosolova, Djam\\'e Seddah", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6b9f1c8680e6c6fb6af9", "title": "Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents", "url": "https://arxiv.org/abs/2610.10062", "authors": "Obada Kraishan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6ad8a7d4b4b5a2944ae0", "title": "Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation", "url": "https://arxiv.org/abs/2607.04576", "authors": "Theodore O. Cochran", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6a0287135a383c847389", "title": "Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station", "url": "https://arxiv.org/abs/2610.08927", "authors": "Wenyu Du, Stephen Chung", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "694b58d304d01102ee50", "title": "Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference Optimization", "url": "https://arxiv.org/abs/2610.09964", "authors": "Antony Dalmiere (LAAS-TRUST), Pascal Marchand (LAAS-TRUST, INSA Toulouse), Guillaume Auriol (LAAS-TRUST, INSA Toulouse), Vincent Nicomette (LAAS-TSF, LAAS)", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6925a4db7d7a4fe9126d", "title": "Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent Decisions", "url": "https://arxiv.org/abs/2610.09890", "authors": "Akira Kitaoka", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "68abe8f2104ff415b1fd", "title": "SwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance by Individually Benign-Looking Agent Populations", "url": "https://arxiv.org/abs/2610.09138", "authors": "Vahid Tavakkoli, Kabeh Mohsenzadegan, Kyandoghere Kyamakya", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6768654339c69a73675c", "title": "Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures", "url": "https://arxiv.org/abs/2610.10126", "authors": "Xinwen Liu, Zhuocheng Pan, Isabella Zhu, Jawei Zhang, Xudong Liu, Tianyu Wo", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6700ae6042b7375d5294", "title": "From Uncertainty to Action: Learning to Steer LLM Agents", "url": "https://arxiv.org/abs/2610.09115", "authors": "Hanwen Li, Jinhao Duan, Guanhua Zhu, Junchi Lu, Bo Shen, Chenxi Yuan, Kaidi Xu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "6365c1b8f0a3f3193060", "title": "Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System", "url": "https://arxiv.org/abs/2610.09021", "authors": "Panagiotis Kasnesis, Christos Chatzigeorgiou, Lazaros Toumanidis, Amalia Contiero Syropoulou", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "62a7d685a7c18c720286", "title": "The Trace Is the State: Exact Credit Assignment for LLM Agent Teams", "url": "https://arxiv.org/abs/2603.06859", "authors": "Yanjun Chen, Yirong Sun, Hanlin Wang, Jinghan Wang, Xinming Zhang, Xiaoyu Shen, Wenjie Li, Wei Zhang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "627d0cd1f95f217cca95", "title": "EDGE: Engine for Deterministic Graph Evaluation through Conversation Simulation from Graph Structured DSL Configuration", "url": "https://arxiv.org/abs/2608.29971", "authors": "Ram Kulathumani, Pushkar Nagar, Regunathan Radhakrishnan, Anupam Tripathi, Xiangbo Mao, Roshanak Omrani, Keshav Somani, Shwet Kamal Mishra, Shayna Lurya", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "61533402ff94cf1a9d65", "title": "SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles", "url": "https://arxiv.org/abs/2610.09832", "authors": "Yuyao Ge, Yiwei Wang, Yuchen He, Baolong Bi, Lingrui Mei, Jiayu Yao, Lizhe Chen, Shenghua Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "5dd5290d109f40455330", "title": "CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems", "url": "https://arxiv.org/abs/2601.05520", "authors": "Xuemei Tang, Chengxi Yan, Jinghang Gu, Chu-Ren Huang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "5bef4b09d011e5fdaa2a", "title": "Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents", "url": "https://arxiv.org/abs/2610.09590", "authors": "Hong Su", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "5b904dc9fddfa63b04ee", "title": "TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning", "url": "https://arxiv.org/abs/2610.09360", "authors": "Ruochi Li, Jianzhe Lin, Haoxuan Zhang, Haihua Chen, Junhua Ding, Edward Gehringer, Yang Zhang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "5b72e6f1f324ee57379d", "title": "Measuring the Creativity of Frontier LLMs in Automated Research", "url": "https://arxiv.org/abs/2609.14057", "authors": "Yiheng Zhao, Mengzhuo Chen, Chengming Hu, Pengyi Liao, Yihan Huang, Yiran Pang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "5a87e487d068692575ad", "title": "Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files", "url": "https://arxiv.org/abs/2610.09264", "authors": "Yupu Wang, Zhengyuan Jiang, Reachal Wang, Neil Zhenqiang Gong", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development", "Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "583f5aaf5a67b0e4e111", "title": "On-Policy Distillation Teaches New Skills but Not New Knowledge", "url": "https://arxiv.org/abs/2610.09639", "authors": "Yixuan Tang, Yi Yang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "550a5faba564be9b65ba", "title": "Noise Your Prompt: Noising Conditioning Tokens in Continuous Diffusion Language Models", "url": "https://arxiv.org/abs/2610.09145", "authors": "Justin Jung", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "53e3f761f6a0e8c3dacf", "title": "LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets", "url": "https://arxiv.org/abs/2610.09872", "authors": "Jun Zhao, Leiming Fu, Yanbo Wen, Yiding Wang, Xuantong Liu, Yang Shu, Yuyang Lu, Xuanran Xing, Jingqi Tong, Hao Xu, Qi Zhang, Xuanjing Huang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "5233473fbfabc44f6137", "title": "Generating Edit-Inducing Questions for AI Research Manuscripts", "url": "https://arxiv.org/abs/2609.36617", "authors": "Sebastian Joseph, Zichao Wang, Jennifer Healey, Alexa Siu, Junyi Jessy Li, Ani Nenkova", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "521efabb40f332fad057", "title": "Defensive Sufficiency in a Stackelberg Model of AI Security", "url": "https://arxiv.org/abs/2610.09892", "authors": "Subhabrata Majumdar, Rajlakshmi Chavan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "4e779b73ad099677b443", "title": "SWE-Game: Can Coding Agents Build the Games We Want?", "url": "https://arxiv.org/abs/2609.33678", "authors": "Xiaoyu Chen, Lai Wei, Jin Wang, Xiangyu Zou, Ruochen Fan, Enze Luo, Mingzhe Yao, Jiahui Zhu, Yuhua Wen, Linghe Kong, Weiran Huang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "4d0f1fed9664a45c22e8", "title": "Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation", "url": "https://arxiv.org/abs/2604.17260", "authors": "Yihang Li, Chenhui Chu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "4915f2554a5bd5a48698", "title": "Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models", "url": "https://arxiv.org/abs/2606.30899", "authors": "Arash Raftari, Mehrdad Mahdavi, Nathan Blackthorn, Andrew Arash Mahyari", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "48f1bcddaf72229f91b5", "title": "DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies", "url": "https://arxiv.org/abs/2610.09144", "authors": "Kaixi Feng, Guoheng Sun, Ziyao Wang, Yexiao He, Zheyu Shen, Ang Li", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "4881074a18059681c686", "title": "Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment", "url": "https://arxiv.org/abs/2610.08482", "authors": "Maryam Baizhigitova, Andrew Seohwan Yu, Po-Hao Chen, Naveen Subhas, Sixu Chen, Xinxin Wang, Kunio Nakamura, Richard Lartey, Xiaojuan Li, Mingrui Yang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "48591a11a1abb7bba2da", "title": "AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails", "url": "https://arxiv.org/abs/2610.08923", "authors": "Melissa Kazemi Rad, Sihui Dai, Isha Slavin, Kushal Chawla, Mann Patel, Jian Ni, William M. Campbell, Stephen Rawls, Sambit Sahu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "47b726c0db98074d7fa0", "title": "Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora", "url": "https://arxiv.org/abs/2610.10170", "authors": "Andrey Kuehlkamp, Priscila Correa Saboia Moreira, Samuel Rund", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "471c1f201f5e3afce485", "title": "RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents", "url": "https://arxiv.org/abs/2610.06401", "authors": "Mohamed Dhouib, Clement Elliker, Alexi Canesse, Ma\\\"el Jenny, Lucas-Andrei Thil, Mahammed El Sharkawy, Sonia Vanier, Elie Bursztein", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Agents & automation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "46d793196669f8f6a6fd", "title": "Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH", "url": "https://arxiv.org/abs/2606.13994", "authors": "Vikhyath Kothamasu, Virginia Smith, Chhavi Yadav", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "466478eb0e578a4c04a2", "title": "CoDR: Training-Free Confidence-Drift Remasking for Diffusion Language Models", "url": "https://arxiv.org/abs/2610.08833", "authors": "Yue Wu, Qinghe Zhang, Yu Zhang, Jian Huang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "460743e6f87321b0202e", "title": "GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks", "url": "https://arxiv.org/abs/2610.09112", "authors": "Gabriel Diaz-Ireland, Diego Prieto-Herr\\'aez, Mario Garc\\'ia Peces, Javier Vel\\'azquez, Benjamin Zaitchik, Devika Jain", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "44d3bb0045c4c9f79f45", "title": "Comprehension Audits to Mitigate Risks from Automated AI Research", "url": "https://arxiv.org/abs/2610.10064", "authors": "Ronald J. Bodkin, Bahrad A. Sokhansanj, Gillian K. Hadfield", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "43fbe60f9de565d7f61f", "title": "Towards Explainable Conversational AI for Early Diagnosis with Large Language Models", "url": "https://arxiv.org/abs/2512.17559", "authors": "Maliha Tabassum, M Shamim Kaiser", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "41d88859a57767b4a216", "title": "A Relative-Computability Theory of Self-Improving Agents", "url": "https://arxiv.org/abs/2605.27381", "authors": "Chien-Ping Lu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "3f8c4424303b37f14f65", "title": "Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models", "url": "https://arxiv.org/abs/2610.10478", "authors": "Tan Yu, Alexander Bukharin, Khushi Bhardwaj, Jennifer Williams, Zirui Liu, Jonathan Lingjie Li, Soumye Singhal, Joseph Jennings, Sanjeev Satheesh, Yash Jain, Ashish Vaswani, Venkat Krishna Srinivasan, Matthew Papakipos, Hyunwoo Kim, Jian Zhang, Oleksii Kuchaiev, Markus Kliegl, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jonathan Cohen, Jiantao Jiao", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "3c68746962d8cad23f6a", "title": "Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method", "url": "https://arxiv.org/abs/2609.35965", "authors": "Yunzhe Xu, Zhe Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "3b6d6cc4fb9fac074a69", "title": "A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with Transformers", "url": "https://arxiv.org/abs/2610.09529", "authors": "Nadhem Zmandar, Mo El-Haj, Paul Rayson", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "3946f43dd6dbfccf0ac8", "title": "SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning", "url": "https://arxiv.org/abs/2610.10304", "authors": "Mingyan Liu, Min Huang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "38574a0241a37c8e45c2", "title": "The Attribution Blind Spot: Layerwise Trajectory Diagnostics for Source Reliance in Retrieval-Augmented Language Models", "url": "https://arxiv.org/abs/2610.09493", "authors": "Zhe Yu, Wenpeng Xing, Yunzhao Wei, Bo Yang, Chen Ye, Gaolei Li, Meng Han", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "35fd55e0d64fe1cb0836", "title": "LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure", "url": "https://arxiv.org/abs/2608.13545", "authors": "Fanfei Li, Jana Zeller, Manuel Prada-Corral, Thadd\\\"aus Wiedemer, Prasanna Mayilvahanan, Ryan Cotterell, Wieland Brendel", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Search & knowledge", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "2eacf7963c327eb8e526", "title": "Learning to Accumulate Knowledge with Mutual Information", "url": "https://arxiv.org/abs/2610.10042", "authors": "Yuyang Zhao, Lizi Liao, Leyang Shen, Xiaoyan Zhao, Yang Zhang, Fuli Feng, Xiangnan He", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "2c0156c2a7b2dd806e44", "title": "BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks", "url": "https://arxiv.org/abs/2606.24162", "authors": "Jin Huang, Yutong Xie, Wanli Song, Xingjian Zhang, Walter Yuan, Matthew O. Jackson, Qiaozhu Mei", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "2abc41ee98fd1e5d6252", "title": "Humanize: Judgement Engineering for Agentic Coding", "url": "https://arxiv.org/abs/2610.08900", "authors": "Sihao Liu, Ligeng Zhu, Zijian Zhang, Dongyun Zou, Zhengyang Zhang, Changye Li, Song Bian, Song Han, Tony Nowatzki", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "29f07e1646bc482bcbee", "title": "The \\`{I}r\\`{o}y\\`{i}nSpeech Text Corpus: 24,905 Curated Yor\\`ub\\'a Sentences for Speech and Language Technology", "url": "https://arxiv.org/abs/2610.05366", "authors": "Kola Tubosun, Aanuoluwapo Aremu, Tolulope Ogunremi, Iroro Orife, David Ifeoluwa Adelani", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "2983055bf664452201e5", "title": "Auditing generative audio calls for known-task audio-llm evaluation", "url": "https://arxiv.org/abs/2608.27817", "authors": "Mengzhe Geng", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "29603d21da1eb6c79c93", "title": "Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval", "url": "https://arxiv.org/abs/2509.00141", "authors": "Anuraj Maurya", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Search & knowledge", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "282883ccd3336910c9da", "title": "Document Optimization for Black-Box Retrieval via Reinforcement Learning", "url": "https://arxiv.org/abs/2604.05087", "authors": "Omri Uzan, Ron Polonsky, Douwe Kiela, Christopher Potts", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Search & knowledge", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "28069d508ab4f4c0f816", "title": "HGP:An on-device personalized agent memory via hybrid graph storage", "url": "https://arxiv.org/abs/2610.10071", "authors": "Ran Zhou, Xueming Han, Jiaheng Liu, Yuyao Zhang, Fanyu Meng, Junlan Feng, Yuxiang Ren", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "27e0a39b9daed2d841f8", "title": "Large language models are vulnerable to incidental information in clinical documentation and reasoning", "url": "https://arxiv.org/abs/2610.08585", "authors": "Krithik Vishwanath, Brandon Ye, Anton Alyakin, John E. Markert, Aaron Hsieh, Micha{\\l} Ma\\'nkowski, Eric K. Oermann", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "27847d0dd33b62668be5", "title": "Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos", "url": "https://arxiv.org/abs/2610.04432", "authors": "Jinzhou Tang, Zijun Zhang, Jing Yang, Yuchen Yan, Kun Zhou, Lingjun Mao, Ruobing Han, Jinglin Cao, Wenpeng Xu, Lukun He, Minghao Fu, Fan Feng, Biwei Huang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "27537bb4606358bb1d70", "title": "CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search", "url": "https://arxiv.org/abs/2610.09212", "authors": "Guanhua Ding, Zi Wang, Ruichao Li, Jack Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "2698d471c63b79143378", "title": "RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment", "url": "https://arxiv.org/abs/2610.09294", "authors": "Tianruo Rose Xu, Jiawei Ren, Yichi Yang, Zhaoxu Zheng, Lianhui Qin", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "25f3313a6abd695935fd", "title": "Routing-Aware Safety Alignment for Mixture-of-Experts Models", "url": "https://arxiv.org/abs/2602.04448", "authors": "Jiacheng Liang, Yuhui Wang, Tanqiu Jiang, Ting Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "259781ee7fc4dac59c40", "title": "RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents", "url": "https://arxiv.org/abs/2610.09088", "authors": "Mayur Akewar, Ravi Ranjan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "256ec415fdba134af806", "title": "RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation", "url": "https://arxiv.org/abs/2610.10120", "authors": "Hengbo Xiao, Boyao Zhang, Purui Liu, Yuxuan Zheng, Haoran Yin, Haibo Liu, Fan Zhang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "240ed951b6ab5e3c24d2", "title": "OTel: Open Telco AI Datasets, Benchmarks, and Models", "url": "https://arxiv.org/abs/2610.07766", "authors": "Farbod Tavakkoli, Gregory Diamos, Kenneth Church, David Kanter, Mark Austin, Imtiaz Karim, Mirza Masfiqur Rahman, Merouane Abdelkader Debbah, Zeinab Nezami, Ali Maatouk, Leandros Tassiulas, Rex Ying, Nick Sorros, Louis Powell, Nikolaos Vasiloglou, Ashish Vaswani, Somanshu Singla, Adarsh Chaluvaraju", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "2230d921ada063c5120d", "title": "A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty Quantifiers", "url": "https://arxiv.org/abs/2610.09693", "authors": "Evgenia Ilia, Wilker Aziz", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1fa9b0d8ece69f93c427", "title": "StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement", "url": "https://arxiv.org/abs/2606.00267", "authors": "Junwon Seo, Sushant Veer, Ran Tian, Wenhao Ding, Apoorva Sharma, Karen Leung, Edward Schmerling, Marco Pavone, Andrea Bajcsy", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1f7f36623bcf9295e9c8", "title": "Document-Level Text Simplification in Estonian Using Large Language Models", "url": "https://arxiv.org/abs/2610.10378", "authors": "Meeri-Ly Muru, Eduard Barbu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1f569df9c3636209e377", "title": "Large Distant Gradients Need Not Be Reliable: reliability-weighted credit assignment for long-horizon autoregressive forecasting", "url": "https://arxiv.org/abs/2609.12890", "authors": "Junhao Zhao, David Michael Simberg, Jacob Kang, Colin Connor Kurniawan, Nan Xu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1d326af93ce15955e9b4", "title": "Do Language Models Need Music Supervision? Verifiable Rewards for Multi-Constraint Symbolic Music Generation", "url": "https://arxiv.org/abs/2609.23665", "authors": "Haoyue Liu, Xiaoying Tang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1bea3cfa8c3c52471b38", "title": "Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice Evaluation", "url": "https://arxiv.org/abs/2610.10368", "authors": "Yibei Guo, Rui Liu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1ac59b9b556a1fa5ba6c", "title": "U-Space: Uncovering When and Why Uncertainty Arises in Language Models", "url": "https://arxiv.org/abs/2610.09087", "authors": "Tobias Braun, Nils Loose, Alexander Herzog, Virginia Ceccatelli, Marcus Rohrbach, Thomas Eisenbarth, Lorenzo Cavallaro", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "19c18dfd8e93342d2bdf", "title": "Just on Time: Token-Level Early Stopping for Diffusion Language Models", "url": "https://arxiv.org/abs/2602.11133", "authors": "Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi, Serhii Dmytryshyn, Dmytro Khamula, Michal Zakrzewski, Damian Rynczak, Jacek Ma{\\l}ecki, Taras Rumezhak, Volodymyr Karpiv", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "179482683d37f8ff3ada", "title": "RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy", "url": "https://arxiv.org/abs/2605.02003", "authors": "Mario Koddenbrock, Christoph Lange, Robin Legner, Martin J\\\"ager, Martin K\\\"ogler, Mariano N. Cruz Bournazou, Peter Neubauer, Felix Biessmann, Erik Rodner", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1587eadd0e9f907949b2", "title": "When Algorithmic Exploration Becomes Cheap: A Case Study of Agentic Research in EDA", "url": "https://arxiv.org/abs/2610.10129", "authors": "Keren Zhu, Yu Deng, Xiaoyu Hao, Liwen Jiang, Zijian Jiang, Cunqing Lan, Boxiang Song, Pujun Su, Yaojia Wang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "14f1faabc555f3b5aa41", "title": "Is Word Error Rate Enough? Rethinking Privacy Evaluation in Speech with Entity-Aware Metrics", "url": "https://arxiv.org/abs/2610.08831", "authors": "Anjana Rajasekhar, Jule Pohlhausen, Nayana Jacob Alappattu, Anna Leschanowsky", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "14e87bdc08ea82e4eb04", "title": "Healthy skepticism in AI: a data visualization research agenda", "url": "https://arxiv.org/abs/2610.09740", "authors": "G. Elisabeta Marai, Marc Baaden, Michael Behrisch, Michael Krone, Pere-Pau V\\'azquez", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "13299bd37ccc78efc7e0", "title": "Inverting Multi-Vector Visual Document Indices", "url": "https://arxiv.org/abs/2610.09920", "authors": "Zhuchenyang Liu, Yao Zhang, Yu Xiao", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "13256c818280296e7e5e", "title": "Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator", "url": "https://arxiv.org/abs/2607.07993", "authors": "Shiping Yang, Shining Liang, Weihao Liu, Wenbiao Ding, Linjun Shou, Lu Cheng, Angel X. Chang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "130799d69914504e43c8", "title": "MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent", "url": "https://arxiv.org/abs/2610.10355", "authors": "Zekai Liu, Zhilin Wang, Xuzheng He, Yu Cheng, Yang Yang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "12b6216d5542207b7b0f", "title": "From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA", "url": "https://arxiv.org/abs/2610.09361", "authors": "Xiaotian Qiu, Kairui Liu, Shi Chenyi, Jinyuan Deng, Qi Sun, Cheng Zhuo", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Search & knowledge", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1280de4aaf39ea27d7e4", "title": "ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation", "url": "https://arxiv.org/abs/2610.09163", "authors": "Arkajyoti Chakraborty, Aryan Tayal, Ishika Agarwal, Tanner Sorensen, Justin Chiu, Alessandro Di Bari, Neha Gupta, Andreas Stolcke", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "11e95e729ef8fa908a6a", "title": "Transferability and operational reliability of a Prithvi crop classification foundation model under phenological and geographic shift across three continents", "url": "https://arxiv.org/abs/2610.08810", "authors": "Venkatesh Kolluru, Rajat Shinde, Abdelhak Marouane, Caden Helbling, Deepak Shah, Othneil Drew, Srinivas Kolluru, Iksha Gurung, Manil Maskey, Rahul Ramachandran", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "11655474e745dff580ef", "title": "Chronocooked: A Benchmark for Interval Timing in Reinforcement Learning Agents", "url": "https://arxiv.org/abs/2608.16666", "authors": "Amrapali Pednekar, Alvaro Garrido-Perez, Yara Khaluf, Pieter Simoens", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "10e2634a0e0ed0581176", "title": "QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents", "url": "https://arxiv.org/abs/2610.10258", "authors": "Yujin Song, Kaining Zhang, Qixin Zhang, Shuai Wang, Pingchuan Ma, Yuxuan Du", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "1036b5502ef50663a725", "title": "Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution", "url": "https://arxiv.org/abs/2610.09240", "authors": "Wanjing Han, Levi Taiji Li, Mu Zhang, Yue Jiang, Guanhong Tao", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation", "Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "101ea2df1b7555c71e61", "title": "Who Brought Easter Eggs to Eid? Auditing LLM-Generated Cultural Translation of Math Word Problems Across Languages and Regions", "url": "https://arxiv.org/abs/2606.11009", "authors": "Parisa Suchdev, Juniper Lovato", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "10149415446d8f4d0064", "title": "Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference", "url": "https://arxiv.org/abs/2610.07587", "authors": "Shuqing Shi, Ziyan Wang, Milind Tambe, Yali Du", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0e91bf2e5395f2ba5cfb", "title": "CredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents", "url": "https://arxiv.org/abs/2610.08871", "authors": "Rafid Ahmed, Joseph Fioresi, Mubarak Shah, Yuzhang Shang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0e356a57ead4495e0d0f", "title": "Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher Supervision", "url": "https://arxiv.org/abs/2610.10332", "authors": "Wenxi Gan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0e2abfcecf7ffeaa9daa", "title": "Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs", "url": "https://arxiv.org/abs/2604.17502", "authors": "Carissa Cullen, Harry Garland, Alexander Roman, Louis Thomson, Christos Ziakas, Elliott Thornley", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0b075b15fb51cc714843", "title": "InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain", "url": "https://arxiv.org/abs/2610.09671", "authors": "Linqi Zhang, Chong Qi, Yan Cheng, Wanqing Cao, Yu Liu, Chenwei Lin, Xian Xu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0a408b6f89baf9dab04f", "title": "Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification", "url": "https://arxiv.org/abs/2610.09681", "authors": "Shuangjie Yao, Nikolaus Holzer, Mark Paul Santolucito, Baishakhi Ray, Suman Jana, Dongdong She", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0a367258b338a4dddf90", "title": "How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings", "url": "https://arxiv.org/abs/2606.00356", "authors": "Sripad Karne", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "092077237d2f2f1515c9", "title": "An Empirical Study of Agent Skills' Downstream Utility", "url": "https://arxiv.org/abs/2610.08875", "authors": "Yu Cheng, Dehai Zhao, Zhongxin Liu, Qing Huang, Zhenchang Xing, Xiaoxue Ren", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0919e546d77af030ce4a", "title": "Trajectory Abstraction for the Science of Language Agent Behavior", "url": "https://arxiv.org/abs/2610.09237", "authors": "Tianqiang Yan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-cl"], "topics": ["Agents & automation", "Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0914e02681aa98f47eea", "title": "Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting", "url": "https://arxiv.org/abs/2603.11938", "authors": "Chantal Pellegrini, Adrian Delchev, Ege \\\"Ozsoy, Nassir Navab, Matthias Keicher", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Search & knowledge"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "07ee1d95ac1efc03200e", "title": "Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset", "url": "https://arxiv.org/abs/2610.08813", "authors": "Xiao Wang, Yuxiang Zhang, Dan Xu, Yuehang Li, Shiao Wang, Bo Jiang, Yaowei Wang, Yonghong Tian, Jin Tang", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Trust & evaluation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0534d3aaf64466b40a8a", "title": "Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering", "url": "https://arxiv.org/abs/2610.09007", "authors": "Kemal Davaslioglu, Sastry Kompella", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0504944df6daba281072", "title": "Shared and structured inputs undermine collective random choice by reasoning AI agents", "url": "https://arxiv.org/abs/2610.09667", "authors": "Takahiro Ezaki, Naoto Imura, Katsuhiro Nishinari", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "0502fb8f755cd6aae2de", "title": "TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble", "url": "https://arxiv.org/abs/2610.10242", "authors": "Pengfei He, Jiayuan Zhou, Shaowei Wang, Ruiqi Pan", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "041f0df3f5a1ef79a5a6", "title": "Reinforcement Learning for Code Optimization", "url": "https://arxiv.org/abs/2607.25970", "authors": "Pierre Chambon, Kunhao Zheng, Juliette Decugis, Benoit Sagot, Gabriel Synnaeve", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai", "arxiv-lg"], "topics": ["Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "02e5cbe4f84e3f677cdb", "title": "Latent Performance Profiling of Large Language Models", "url": "https://arxiv.org/abs/2605.30018", "authors": "Tanmoy Chakraborty, Ayan Sengupta, Suparna Bhattacharya, Partha Pratim Chakrabarti, Amlan Chakrabarti, Supratik Chakraborty, Partha Pratim Das, Lipika Dey, Richa Singh, Mayank Vatsa", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-cl", "arxiv-lg"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "014195f4e50ca0909557", "title": "EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models", "url": "https://arxiv.org/abs/2606.06379", "authors": "Hao Wang, Qiwei Zeng, Jinghao Lin, Shuchang Ye, Yuezhe Yang, Yige Peng, Haoyuan Che, Jinman Kim, Lei Bi", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Language & documents"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "00d8cd492dd233709b99", "title": "Toward Evidence-Driven Human-Agent-Robot Teaming for Earth-Independent Anomaly Triage", "url": "https://arxiv.org/abs/2610.08933", "authors": "Ignacio G Lopez-Francos, Alexis Gallagher, Samira Shalal", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "00c6e4badb61844a2700", "title": "From Verification Failures to Reusable Guidance for Coding Agents", "url": "https://arxiv.org/abs/2609.39022", "authors": "Yuqing Zhai, Xiaohong Chen, Lingming Zhang, Sriram Vishwanath, Grigore Rosu", "published": "2026-10-08T04:00:00Z", "publisher": "arXiv", "source_ids": ["arxiv-ai"], "topics": ["Agents & automation", "Coding & development"], "license": "CC0 metadata", "license_url": "https://info.arxiv.org/help/license/index.html#metadata-license"}, {"id": "e83061b75550cc4013dc", "title": "Sunsetting api.creativecommons.org", "url": "https://opensource.creativecommons.org/blog/entries/2026-05-06-sunsetting-api/", "authors": "TimidRobot", "published": "2026-05-06T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "8a1eae7b28c78131b9b0", "title": "Deprioritizing work programs", "url": "https://opensource.creativecommons.org/blog/entries/2026-03-11-deprioritizing-work-programs/", "authors": "TimidRobot", "published": "2026-03-11T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "3a1952eef5b9be9bd58b", "title": "Quantifying the Commons: The end of an era", "url": "https://opensource.creativecommons.org/blog/entries/2026-30-03-the-end-of-an-era/", "authors": "Oreoluwa", "published": "2026-03-03T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "1c8c2315bee1e8d70afe", "title": "Quantifying the Commons: My Journey so far with outreachy", "url": "https://opensource.creativecommons.org/blog/entries/2026-01-22-My-outreachy-journey/", "authors": "Oreoluwa", "published": "2026-01-22T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "58f34803658584802218", "title": "Avoiding generative AI development tools", "url": "https://opensource.creativecommons.org/blog/entries/2025-12-01-avoiding-gen-ai-tools/", "authors": "TimidRobot", "published": "2025-12-01T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "02576f5d3597660fedf6", "title": "Refactoring and Releasing the new CC Chooser: Part 2", "url": "https://opensource.creativecommons.org/blog/entries/2025-10-06-refactoring-the-cc-chooser-pt-2/", "authors": "sara", "published": "2025-10-06T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "17b46576c95881e9b764", "title": "Refactoring and Releasing the new CC Chooser: Part 1", "url": "https://opensource.creativecommons.org/blog/entries/2025-07-11-refactoring-the-cc-chooser-pt-1/", "authors": "sara", "published": "2025-07-11T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "0c55a0af938a36e42f34", "title": "Migrating from MariaDB 10.4 to 10.11 on AWS RDS", "url": "https://opensource.creativecommons.org/blog/entries/2025-03-06-AWS-RDS-blog-post/", "authors": "shafiya", "published": "2025-03-24T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "64ba318731a206e1aaeb", "title": "Reflecting On My Outreachy Journey With Creative Commons", "url": "https://opensource.creativecommons.org/blog/entries/reflecting-on-my-outreachy-journey-with-creative-commons/", "authors": "Queen", "published": "2025-02-27T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "5d81f567aed63b78fc29", "title": "Finding Problems, and Exercising Compassion", "url": "https://opensource.creativecommons.org/blog/entries/2025-02-04-finding-solutions-exercising-compassion/", "authors": "sara", "published": "2025-02-04T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "17a2f0757da4d7d50926", "title": "Outreachy Midpoint Progress With Creative Commons", "url": "https://opensource.creativecommons.org/blog/entries/outreachy-midpoint-progess-with-creative-commons/", "authors": "Queen", "published": "2025-01-19T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "f84d2d842c90a03a45c1", "title": "Skipping Google Summer of Code (GSoC) 2025", "url": "https://opensource.creativecommons.org/blog/entries/2025-01-15-skipping-gsoc-2025/", "authors": "TimidRobot", "published": "2025-01-15T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "28d8cee4a5e23b9cc0a1", "title": "My Outreachy Internship With Creative Commons", "url": "https://opensource.creativecommons.org/blog/entries/my-outreachy-internship-with-creative-commons/", "authors": "Queen", "published": "2024-12-10T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "aa2537b09a189c9bcc39", "title": "Local Environment Creation using Ansible and Docker: Part 2", "url": "https://opensource.creativecommons.org/blog/entries/2024-08-23-create-local-ansible-dev-env/", "authors": "amandayclee", "published": "2024-08-23T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "ef4f2da1c34d8aebb504", "title": "Automating Quantifying the Commons: Part 2", "url": "https://opensource.creativecommons.org/blog/entries/2024-08-22-automating-quantifying/", "authors": "NaishaSinha", "published": "2024-08-22T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "07d399b1c1f13b617db2", "title": "Continuing Open Collaboration: GSoC 2024 With Creative Commons", "url": "https://opensource.creativecommons.org/blog/entries/continuing-open-collaboration-gsoc-2024-with-creative-commons/", "authors": "Murdock9803", "published": "2024-08-22T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "22e5a031bb160c24a6c0", "title": "Local Environment Creation using Ansible and Docker: Part 1", "url": "https://opensource.creativecommons.org/blog/entries/2024-07-19-create-local-ansible-dev-env/", "authors": "amandayclee", "published": "2024-07-18T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "2ec128c8a23c7178cff6", "title": "Automating Quantifying the Commons: Part 1", "url": "https://opensource.creativecommons.org/blog/entries/2024-07-10-automating-quantifying/", "authors": "NaishaSinha", "published": "2024-07-10T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "1579131e74b987725b7e", "title": "Empowering Open Knowledge: GSoC 2024 With Creative Commons", "url": "https://opensource.creativecommons.org/blog/entries/empowering-open-knowledge-gsoc-2024-with-creative-commons/", "authors": "Murdock9803", "published": "2024-07-10T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "d62a4d76c3293d27353a", "title": "New CreativeCommons.org launched 2023 September", "url": "https://opensource.creativecommons.org/blog/entries/2024-05-28-creativecommons-org/", "authors": "sara', 'shafiya', 'TimidRobot", "published": "2024-05-28T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "616f922668b4b4e79ff2", "title": "CC Legal Tools: Machine-Readable Layer", "url": "https://opensource.creativecommons.org/blog/entries/2023-08-25-machine-layer/", "authors": "saurabh", "published": "2023-08-28T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "c32c9bc47313812a5a03", "title": "New Chapter of My Professional Life", "url": "https://opensource.creativecommons.org/blog/entries/2023-06-16-new-chapter-of-my-professional-life/", "authors": "shafiya", "published": "2023-06-20T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "b9028a342491cda06122", "title": "Many Mona Lisas? Artistic Data Quantification and Assessment", "url": "https://opensource.creativecommons.org/blog/entries/2023-04-26-umsi-how-many-mona-lisas/", "authors": "grace_coleman', 'anthony_ho', 'tyler_phillips', 'claire_wan", "published": "2023-04-26T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "1a644b8a7bd653bfd775", "title": "Considering Community Contributions at Creative Commons", "url": "https://opensource.creativecommons.org/blog/entries/2023-03-24-community-contributions/", "authors": "sara", "published": "2023-03-24T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "cfb684e45a55d92a93b8", "title": "Outreachy Internship Mid-point Progress Update", "url": "https://opensource.creativecommons.org/blog/entries/2023-02-01-outreachy-mid-point/", "authors": "precious", "published": "2023-02-01T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "c6ead44330c509391e71", "title": "How I Landed My First Internship With Outreachy", "url": "https://opensource.creativecommons.org/blog/entries/2023-01-04-how-i-landed-my-first-internship/", "authors": "precious", "published": "2023-01-04T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "08fc57794321bddd1e8a", "title": "Thinking More Openly About Working in The Open", "url": "https://opensource.creativecommons.org/blog/entries/2022-12-16-new-to-working-in-open/", "authors": "sara", "published": "2022-12-16T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "5fd614649a4f48db9aab", "title": "Data Science Discovery: Quantifying the Commons", "url": "https://opensource.creativecommons.org/blog/entries/2022-12-07-berkeley-quantifying/", "authors": "Dun-MingHuang', 'ShuranYang", "published": "2022-12-07T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "9a40de435406b1c7d45f", "title": "CalVer to SemVer", "url": "https://opensource.creativecommons.org/blog/entries/2022-11-11-calver-to-semver/", "authors": "TimidRobot", "published": "2022-11-11T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "96c6d69fdeed3b5b7c57", "title": "Building the CC Global Components Library", "url": "https://opensource.creativecommons.org/blog/entries/building-the-cc-global-components-library/", "authors": "MuluhGodson", "published": "2022-03-17T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "3129bb20048161743dda", "title": "CC Messaging Update 2022Q1 (Dropping IRC)", "url": "https://opensource.creativecommons.org/blog/entries/2022-01-06-cc-messaging/", "authors": "TimidRobot", "published": "2022-01-06T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "298719c1496977d6e2e8", "title": "Upcoming Changes to the CC Open Source Community", "url": "https://opensource.creativecommons.org/blog/entries/2020-12-07-upcoming-changes-to-community/", "authors": "kgodey", "published": "2020-12-07T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "44ebed80a0231701aca7", "title": "Vocabulary Landing Page & Usage Guide Final Report", "url": "https://opensource.creativecommons.org/blog/entries/cc-vocabulary-docs-updates-closing/", "authors": "nimishbongale", "published": "2020-12-03T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "8dcca8bc7d7699ee5f50", "title": "Summary: My GSoD 2020 Journey", "url": "https://opensource.creativecommons.org/blog/entries/summary-my-gsod-2020-journey/", "authors": "ariessa", "published": "2020-12-02T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "2b2f3f92a2af7a27ffcf", "title": "Finish Video Presentation, Project Report and Evaluation Form", "url": "https://opensource.creativecommons.org/blog/entries/finish-video-presentation-project-report-and-evaluation-form/", "authors": "ariessa", "published": "2020-12-01T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "bdf7e304956f908e61a6", "title": "Presenting CC Base docs - A WordPress Base Theme Usage Guide for the CC Base Theme", "url": "https://opensource.creativecommons.org/blog/entries/cc-wp-base-theme-docs-launch/", "authors": "JackieBinya", "published": "2020-11-27T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "2c9940983e40ea639bcf", "title": "Vocabulary Site Updates (Part 3/n)", "url": "https://opensource.creativecommons.org/blog/entries/cc-vocabulary-docs-updates-3/", "authors": "nimishbongale", "published": "2020-11-25T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "5f14d46fa6f017889f43", "title": "Finish GSoD Tasks and Explore CC Catalog Documentation", "url": "https://opensource.creativecommons.org/blog/entries/finish-gsod-tasks-and-explore-cc-catalog-documentation/", "authors": "ariessa", "published": "2020-11-20T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "f9f2d1a1a85bebb168b6", "title": "Content Creation Phase: WordPress Base Theme Usage Guide", "url": "https://opensource.creativecommons.org/blog/entries/cc-wp-base-theme-docs-content-creation/", "authors": "JackieBinya", "published": "2020-11-10T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "c44e51f9be0243b1fb12", "title": "Vocabulary Site Mid-Internship Update (v2)", "url": "https://opensource.creativecommons.org/blog/entries/cc-vocabulary-docs-updates-2/", "authors": "nimishbongale", "published": "2020-11-09T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "e23c07260b3f107a26d8", "title": "Restructure README and Add Documentation Guidelines", "url": "https://opensource.creativecommons.org/blog/entries/restructure-readme-and-add-documentation-guidelines/", "authors": "ariessa", "published": "2020-11-05T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "053e4a5b2da338852cad", "title": "Vocabulary Site Updates (v1)", "url": "https://opensource.creativecommons.org/blog/entries/cc-vocabulary-docs-updates-1/", "authors": "nimishbongale", "published": "2020-10-26T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "810a9c166fbc63ac3373", "title": "Add New Sections, Descriptions, Help Texts, Code Examples, Schemas, and Serializers", "url": "https://opensource.creativecommons.org/blog/entries/add-new-sections-descriptions-help-texts-code-examples-schemas-and-serializers/", "authors": "ariessa", "published": "2020-10-21T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "d2909665576e87cd0cb2", "title": "Add Response Samples and Descriptions for API Endpoints", "url": "https://opensource.creativecommons.org/blog/entries/add-response-samples-and-descriptions-for-api-endpoints/", "authors": "ariessa", "published": "2020-10-09T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "b2d2505e1ef99b641912", "title": "Vocabulary Site & Usage Guide Introduction (GSoD'20)", "url": "https://opensource.creativecommons.org/blog/entries/cc-vocabulary-docs-intro/", "authors": "nimishbongale", "published": "2020-10-02T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "c01e3d4b5f5a95c72693", "title": "Creative Commons WordPress plugin: attribution for images", "url": "https://opensource.creativecommons.org/blog/entries/cc-wp-plugin-attribution-for-images/", "authors": "rczajka", "published": "2020-10-01T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "37947fb278e068e8c10d", "title": "WordPress Base Theme Usage Guide (GSOD-2020): Hello World!", "url": "https://opensource.creativecommons.org/blog/entries/cc-wp-base-theme-docs-intro/", "authors": "JackieBinya", "published": "2020-09-30T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "c4c7dab7b7df851e30f8", "title": "Add Query Using curl Command and Provide Response Samples", "url": "https://opensource.creativecommons.org/blog/entries/add-query-using-curl-command-and-provide-response-samples/", "authors": "ariessa", "published": "2020-09-25T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "9b55c86c7253232af6b2", "title": "The specifics - Revamping CCOS", "url": "https://opensource.creativecommons.org/blog/entries/the-specifics-revamping-CCOS/", "authors": "dhruvi16", "published": "2020-09-02T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}, {"id": "659ffd89e645ce8ab781", "title": "Accessibility and Internationalization: WrapUp GSoC 2020", "url": "https://opensource.creativecommons.org/blog/entries/cc-search-accessibility-wrapup/", "authors": "AyanChoudhary", "published": "2020-08-31T00:00:00Z", "publisher": "Creative Commons Open Source", "source_ids": ["cc"], "topics": ["Open source"], "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}], "selection_method": "AI/language research feed titles matched to documented topic keywords; CC Open Source entries included. No generated summaries or quality ratings."}