Overview

Self-improving agents study how systems can learn from their own actions and outcomes to perform better on later tasks, from coding and web use to robotics and long-horizon games. Common approaches turn successes and failures into reusable memories or executable skills, revise prompts and agent harnesses, or update model parameters through fine-tuning and reinforcement learning. Work increasingly uses repeated trials, held-out tasks, execution-based checks, and external evaluators to test whether improvements transfer rather than merely exploit a score. The central tension is that feedback and self-authored tests can be unreliable, so genuine progress must be balanced against regression, reward hacking, safety risks, and the cost of verification.

Latest papers

CardsList

198 papers31 papers in the last four weeks, down 47% on the four weeks before. 0.2% of all new papers.

  1. Do LLM Agents Still Need to Be Told How to Self-Improve?

    Nov 17, 2026Shobhita Sundaram, Cansu Sancaktar, Phillip IsolaLLM Agent Self-ImprovementSelf-Improving Agents

  2. The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements

    Nov 17, 2026Yuanhao Zeng, Shaocheng Lan, Ao Lu +8Self-Improving AgentsLLM Agent Evaluation

  3. Values Shape What Self-Improving Coding Agents Build

    Nov 17, 2026Jason Liang, Dylan Waldner, Risto MiikkulainenSelf-Improving AgentsAI Coding Agents

  4. Evaluation-Free Recursive Self-Improvement for Coding Agents

    Nov 16, 2026Zhe Ren, Guowei Rong, Yimeng Chen +5AI Coding AgentsSelf-Improving Agents

  5. From Recursion to Convolution: Parallel Self-Improvement for Multi-Agent Systems

    Nov 16, 2026Zheng Wang, Yuang Liu, Sachith Abeywickrama +7Self-Improving AgentsMulti-Agent Systems

  6. ESI: An Embodied Self-Improvement Flywheel for LLM-VLA Agents

    Nov 13, 2026Yundi Cai, Zihan Wang, Chenxi Han +3LLM Agent Self-ImprovementSelf-Improving Agents

  7. RecurIR: Learning When and How to Revise Restoration Policies via Recursive Self-Improvement

    Nov 13, 2026Hu Gao, Haoran Zhang, Yulong Chen +1Agent-Based Image RestorationSelf-Improving Agents

  8. AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning

    Nov 13, 2026Simon Tang, Wenjie Shi, Yongjing Yin +8adaptive reinforcement learningReinforcement Learning

  9. Reward-Driven Collider Physics Challenges for Self-Improving Agentic AI via Reinforcement Learning

    Nov 11, 2026Alexander Yue, Qibin Liu, Julia GonskiAI Agents for Scientific DiscoverySelf-Improving Agents

  10. Verify by Doing: Co-Evolving Agent Execution and Evaluation without External Feedback

    Nov 11, 2026Yitong Lin, Jianda Chen, Yihao Hu +5LLM Agent VerificationSelf-Improving Agents

  11. Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

    Nov 10, 2026Wenji Fang, Yao Lu, Jinghua Wang +1Electronic Design AutomationSelf-Improving Agents

  12. ReSkill: Selective Self-Improvement for Robot Manipulation

    Nov 7, 2026Zheng Sun, Zhihao Li, Zhuo Li +3Robot Skill LearningSelf-Improving Agents

  13. Recursively Self-Improving Electromagnetic Spectrum Agents: Architecture and Operation

    Nov 6, 2026Baolin Chong, Dongfang Xu, Qiaosi Wang +2Self-Improving AgentsRecursive Self-Improvement

  14. A Controlled Study of Models, Skills, Feedback, and Curriculum in Agentic Robotics

    Nov 6, 2026Kaiyuan Chen, Xinyue Zhu, Shuangyu Xie +7Agentic AI for RoboticsCoding Agents

  15. Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement

    Nov 5, 2026Wenbo Huang, Jianxin Bi, Shunyu Yang +10Self-Improving AgentsBenchmark Contamination

  16. Reimagining computational quantum research with AI scientists

    Nov 2, 2026Yuxuan Du, Hanqing Zhao, Xinbiao Wang +3AI Agents for Scientific DiscoverySelf-Improving Agents

  17. SelfImprove-Bench: Evaluating Generalization in Self-Improving Agents

    Nov 2, 2026Bangrui Xu, Jie Yang, Sidi Chen +6Self-Improving AgentsAI Agent Evaluation

  18. Recursive Self-Improvement of Exoskeleton Assistance Policies through Human-in-the-Loop Feedback

    Nov 1, 2026Muyuan Ma, Shuo Jiang, Lijun Han +5Assistive RoboticsRobot Policy Adaptation

  19. KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents

    Oct 29, 2026Xinhua Miao, Yuanzhen Rong, Weiru Zhang +1LLM AgentsSelf-Improving Agents

  20. MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery

    Oct 29, 2026Yikun Zhang, Xiwei Cheng, Mingze Yuan +15Self-Improving AgentsScientific Workflow Automation

  21. VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation

    Oct 29, 2026Yuan Wang, Yuhang Yu, Mengting Chen +4Agentic Image GenerationSelf-Improving Agents

  22. Recursive Self-Improvement in Physical AI: Mechanisms, Evidence, and Evaluation

    Oct 28, 2026Xiaofeng Han, Kaize Luo, Zenghuang Fu +6Self-Improving AgentsRecursive Self-Improvement

  23. When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement

    Oct 27, 2026Hao Chen, Yukun Yan, Ziyu Han +7Self-Improving AgentsAgent Harness Optimization