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. VISTA: Active Exploration for Self-Improvement in Embodied Agents

    Oct 26, 2026Zhang Zhang, Shengjun Zhang, Simin Huang +4Self-Improving AgentsAgent Harness Optimization

  2. From Intelligence to Autonomy: Foundations and Construction of Autonomous Agents for Future Intelligent Systems

    Oct 24, 2026Hongda Zhang, Ziqing Zhou, Yuning Chen +5Agentic AISelf-Improving Agents

  3. Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons

    Oct 22, 2026Yuval Kansal, Karen Ullrich, Polina Kirichenko +4Self-Improving AgentsLLM Self-Correction

  4. Self-Improving Agents with World Model Predictive Paths

    Oct 20, 2026Haori Lu, Tianyu Gao, Yaoyao Liu +1Self-Improving AgentsLLM Agent Planning

  5. VibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System Improvement

    Oct 19, 2026Ruotian Peng, Yuanyi Ren, Shuaiqi Liu +7LLM Agent TrainingSelf-Improving Agents

  6. DAGLoop: Aligning Method Design with Experimental Feedback in Automated AI Research

    Oct 18, 2026Dengyuxing Wang, Yonggang Zhang, Qianshu Cai +4Autonomous ExperimentationAutonomous Research Agents

  7. Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research

    Oct 18, 2026Yue Huang, Zhangchen Xu, Xiaonan Luo +16Operations ResearchAutonomous Research Agents

  8. Self-Improving Video-to-Action Models

    Oct 16, 2026Hyunwoo Ryu, Eric Ming Chen, Max Wilcoxson +1Self-Improving AgentsRobot Learning from Video

  9. From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents

    Oct 16, 2026Yewei Zhao, Derong Xu, Wei Chen +6LLM Agent Skill LearningSelf-Improving Agents

  10. Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool Agents

    Oct 16, 2026Litong Feng, Ji Qi, Yiran Cheng +3Tool-Using AgentsSelf-Improving Agents

  11. R2^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop

    Oct 15, 2026Mingda Zhang, Yun Huang, Qiang Huang +7LLM Agent OrchestrationSelf-Improving Agents

  12. MetaShare: Failure-Aware Collective Self-Improvement for Open-Ended Agents

    Oct 15, 2026Vishal Bhutani, Prasang Gupta, Sumanth Chundru +1Self-Improving AgentsSelf-Evolving Agents

  13. The Self-Improvement Problem

    Oct 15, 2026Brian B. Moser, Stanislav Frolov, Tobias C. Nauen +2Self-Improving AgentsRecursive Self-Improvement

  14. Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents

    Oct 14, 2026Yujie Feng, Xiaobin Wang, Jinluan Yang +5Self-Improving AgentsAI Agent Evaluation

  15. AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents

    Oct 14, 2026Peidong Wang, Ying Chang, Zhiming Ma +10Self-Improving AgentsRobotics

  16. MMLA-RSI: Recursive Self-Improvement through RTT and RTMA

    Oct 14, 2026Junyi Zou, Avrova DonzSelf-Improving AgentsRecursive Self-Improvement

  17. EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence

    Oct 13, 2026Wenyi Li, Yizhe Chi, Youjie Zheng +8Self-Improving AgentsRobot Skill Learning

  18. RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation

    Oct 13, 2026Yidi Liu, Haozhe Wang, Jie Xiao +3Self-Improving AgentsCurriculum Learning

  19. ReTerm: Recovery Training for Self-Improving Terminal Agents

    Oct 13, 2026Wei Xie, Kaituo Feng, Shiming Fu +3LLM Agent TrainingSelf-Improving Agents

  20. AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

    Oct 13, 2026Wenhao Zhou, Jiajun Song, Haitao Wang +11Self-Improving AgentsRecursive Self-Improvement

  21. Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents

    Oct 12, 2026Kai Hu, Hua HuangImitation LearningAgent Skill Learning

  22. MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents

    Oct 9, 2026Jingwei Song, Zhisheng Chen, Bingfan Zeng +5AI Agent BenchmarksSelf-Improving Agents

  23. ClawLoop: Self-Improving Agents via Harness-Native Training Loop

    Oct 9, 2026Hansi Yang, Linji Hao, Hongyan Hao +4LLM Agent TrainingSelf-Improving Agents