Publication Certified Long-Horizon Code Agent Evolution via Validation-Gated Skill Optimization Yifan Wang, Hao Cheng, Xiaomin Li, Yuexing Hao, H. Ramesh, Dongwon Jung, Hao Tang, Keru Wang, Chenliang Zhou, Qianhui Wu, Wenlin Yao, Ananth Grama, Andrzej Banburski-Fahey, Baolin Peng, Jaron Lanier, Jianfeng Gao September 2026 arXiv | September 2026
Publication Learning Better Reasoning for Generative Recommendation with Semantic IDs Mengdan Zhu, Yufan Zhao, Sophie Di, Yao Zhao, Tao Di, Yulan Yan, Sridhar Iyer, Liang Zhao September 2026 arXiv | September 2026
Publication CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments Yuxuan Li, Will Epperson, Wesley Deng, Zezhou Huang September 2026 arXiv | September 2026
Publication Reward Hacking Challenges Oversight of Autonomous Research Agents Yue Huang, Zhangchen Xu, Yuchen Ma, Wenjie Wang, Zheyuan Liu, Ziwei Xu, Pin-Yu Chen, Michel Galley, Zinan Lin, S. Feuerriegel, Radha Poovendran, Misha Sra, Alex Pentland, Xiangliang Zhang, Zichen Chen September 2026 arXiv | September 2026
Publication The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks Wenbo Pan, Zhichao Liu, Shujie Liu, Jingying Zeng, Chin-Yew Lin, Xianfeng Tang, Yan Lu, Qi He, Xiaohua Jia September 2026 arXiv | September 2026
Publication A Deeper Look at Depth: Stable Generation Accounting for Quantifier Reasoning Can Cebeci, Nikolaj Bjørner, George Candea, Clément Pit-Claudel September 2026 arXiv | September 2026
Publication Merge++: Universal Merge Refinement Through Data-Free Checkpoint Inversion A. Pola, Vineeth N Balasubramanian September 2026 arXiv | September 2026
Publication Hardness of Online Directed Steiner Network Gary Hoppenworth, Yao-Wei Long, Sepideh Mahabadi, Jakub Tarnawski September 2026 arXiv | September 2026
Publication Uncertainty-Aware RL-Controlled Adaptive 3D Mapping Alpay Ozkan, T. Aydın, Marc Pollefeys, Jelena Trisovic, Dániel Baráth September 2026 arXiv | September 2026
Publication Optimization over covariance matrices with a parameterized metric Yi-Bang Li, Bamdev Mishra, Pratik Jawanpuria, Cyrus Mostajeran September 2026 arXiv | September 2026