LLM Agent Self-Improvement

LLM: Large Language Model

Overview

This field studies how language-model agents can improve across tasks by learning from their own executions, failures, human feedback, or interaction with an environment. Common approaches update prompts, harnesses, skills, memory, or tools while keeping model weights fixed; others use reinforcement learning, self-distillation, or co-evolving tasks and agents. Methods often analyze trajectories to diagnose weaknesses, then test candidate changes with benchmarks, paired comparisons, or held-out regression gates. A central challenge is making gains transfer to new settings without eroding previously reliable behavior, while keeping evaluation trustworthy and improvement costs manageable.

Latest papers

CardsList

298 papers34 papers in the last four weeks, down 51% on the four weeks before. 0.3% of all new papers.

  1. Safe Personal RSI: Evaluating and Repairing Personal-Agent Updates

    Nov 18, 2026Jiapeng Pei, Yuhang Yao, Sitan Liu +9LLM Safety EvaluationLLM Agent Self-Improvement

  2. 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

  3. Values Shape What Self-Improving Coding Agents Build

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

  4. Think Once, Act Fast: Cost-Effective Recursive Self-Improvement for Decision Model Harness

    Nov 17, 2026Siqi Lai, Haitao Li, Hao LiuLLM Agent Self-ImprovementLLM Decision-Making

  5. Inventa: Decentralized Self-Improving Agents for Autonomous Scientific Discovery

    Nov 16, 2026Prithwish Jana, Nikos Kanakaris, Purak Jain +2Autonomous Scientific DiscoveryResearch Idea Generation

  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. AskALCF: A Self-Improving Agentic System for Intelligent HPC User Support

    Nov 11, 2026Jingyan Jiang, Akhilesh Bondapalli, Krishna Rauniyar +7LLM Agent Self-ImprovementFailure Attribution for LLM Agents

  8. RSI-PDEbench: A Benchmark for Self-Improving Agents in PDE Solving

    Nov 11, 2026Binghang Lu, Lang Cao, Changhong Mou +8PDE DiscoveryLLM Agent Self-Improvement

  9. When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

    Nov 10, 2026Runxuan Tang, Haoyu Gao, Yuyan Ding +4LLM Agent Self-ImprovementLLM Agent Memory

  10. The RSI Tax: When Recursive Self-Improvement Is Not Worth the Cost

    Nov 10, 2026Yitong Zhang, Ang Li, Yisen WangLLM Agent Self-ImprovementRecursive Self-Improvement

  11. Trustworthy Recursive Self-Improvement with Statistical Guarantees

    Nov 7, 2026Zihe Gao, Zhengling Qi, Yifan CuiRecursive Self-ImprovementLLM Agent Self-Improvement

  12. CompressionBench: How can your coding agents compress LLMs?

    Nov 4, 2026Xinrui Zhong, Zhifeng Li, Zhiming Wang +7LLM CompressionLLM Agent Self-Improvement

  13. RSI-Env: An Open-Ended Environment for Recursive Self-Improvement of Agents

    Nov 1, 2026Wanying Qu, Zhiyuan Fan, Jiyao Liu +4LLM Agent Self-ImprovementRecursive Self-Improvement

  14. SPAR: Experience-Driven Strategy Evolution in Multi-Session B2B Sales

    Nov 1, 2026Hangming Zhang, Yao Zhao, Haotian Kuang +3LLM Agent Self-ImprovementExperience Learning for LLM Agents

  15. META-Robot: Self-Cognition and Capability Scaling in Agentic Robots

    Oct 30, 2026Xuanzhi Feng, Zeyu Liu, Weiheng Gao +11Agentic AI for RoboticsLLM Agent Self-Improvement

  16. Training LLM Agents to Automate LLM Post-Training with RSI-Dojo

    Oct 29, 2026Shuzheng Gao, Zhaojian Yu, Penghao Yin +4LLM Post-TrainingLLM Agent Self-Improvement

  17. Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents

    Oct 28, 2026Hau-Sing So, Daixian Liu, Weicai LongLLM Agent SafetyLLM Agent Self-Improvement

  18. GEPA-Curator: Curated Learning for Self Improving Agents

    Oct 27, 2026Zack Yu, Nicholas Lee, Minjae Lee +8LLM Agent Self-ImprovementPrompt Optimization

  19. The View from Nowhere: Population-Centered Agent Evolution

    Oct 27, 2026Shuo Yan, Ningning Hou, Haoyu He +2LLM Agent Self-ImprovementSoftware Engineering Agents

  20. Skill∞^{\infty}: Recursive Self-Improvement for Agent Skill Optimization

    Oct 26, 2026Wangcheng Tao, Zhanglu Yan, Han Wu +1LLM Agent Self-ImprovementLLM Agent Skill Learning

  21. RSIV-Harness: A Recursive Self-Improvement Harness Framework for Open-Domain Conversational Text-to-Visualization

    Oct 26, 2026Jiawei Lu, Chen Zhang, Jinwei Lu +3LLM Agent HarnessesLLM Agent Self-Improvement

  22. ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?

    Oct 25, 2026Haojin Wang, Yangzhen Wu, Zeyi Chen +6LLM Agent Self-ImprovementLanguage Model Post-Training

  23. ReGE: Stronger Agents through Experience Synthesis

    Oct 24, 2026Jiarong Liang, Yubo Wang, Zijie Liu +3Experience Learning for LLM AgentsLLM Agent Self-Improvement

  24. RSI Arena: Towards Recursive Self-Improvement with Human Feedback

    Oct 24, 2026Yue Huang, Yanbo Wang, Lichi Li +15LLM Agent Self-ImprovementLLM Agent Training