Overview

Self-evolving agents are systems that use experience from task execution to change how they solve future tasks, rather than relying only on a fixed model or hand-designed workflow. Common approaches store and refine reusable skills or memories, optimize prompts and agent harnesses, train policies with reinforcement learning, or co-evolve task generators, environments, and teams of agents. These methods are tested in settings such as web and GUI use, coding, embodied robotics, scientific workflows, and reasoning benchmarks, with feedback ranging from execution outcomes to verifiers and paired validation. A central challenge is making improvements transfer to new tasks without forgetting earlier abilities or introducing unsafe behavior; reliable evaluation, update verification, and long-term monitoring remain open problems.

Latest papers

CardsList

451 papers45 papers in the last four weeks, down 55% on the four weeks before. 0.3% of all new papers.

  1. How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation

    Oct 26, 2026Christoph Treude, Sebastian BaltesAgent Harness Self-EvolutionLLM Agent Harnesses

  2. EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems

    Oct 25, 2026Yalun Wu, Qiwei Ma, Bingbing Xu +10Multi-Agent SystemsSelf-Evolving Agents

  3. ΔτΔτ-Bench: Pushing Agents Toward a Moving Capability

    Oct 25, 2026Shuofei Qiao, Xuanguang Pan, Yijun Chen +6AI Agent BenchmarksLLM Agent Evaluation

  4. Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning

    Oct 25, 2026Wenzhe Fan, Benjamin Steenhoek, Gaurav Mittal +1Lifelong Learning AgentsAgent Skill Learning

  5. More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents

    Oct 24, 2026Dianxing Shi, Dingjie Fu, Tianyu Lei +1Adaptive Reasoning in Language ModelsEfficient Language Model Reasoning

  6. CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems

    Oct 24, 2026Xufei Shi, Derong Xu, Wei Chen +3Multi-Agent LLM SystemsMulti-Agent Systems

  7. Causal-based approaches to explain and learn from self-extension - A review

    Oct 23, 2026Rebeca Marfil, Pablo Bustos, Antonio BanderaSelf-Evolving AgentsCognitive Architectures for AI Agents

  8. RSIHub: A Composable Framework for Agent-Evolution Methods

    Oct 23, 2026Zimu Wang, Xiaobo Wang, Siyu Ye +11Self-Evolving AgentsLLM Agent Harnesses

  9. VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team

    Oct 22, 2026Wenbo Hu, Ken Li, Jiazhe Wei +13AI Coding AgentsMulti-Agent LLM Systems

  10. ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization

    Oct 22, 2026Zhaoran Feng, Yuchen Ni, Jianan Liu +3AI for ScienceSelf-Evolving Agents

  11. Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core

    Oct 22, 2026Yebo Feng, Jingyang Dai, Liangrui Pan +3Self-Evolving AgentsMulti-Agent LLM Systems

  12. GuideEvolve: Self-Evolving Agent Framework with Expert Guidance and 3Ts Mechanisms

    Oct 21, 2026Meihong Jia, Yasemin Timar, Jonathan TawsSelf-Evolving AgentsLLM Agent Self-Improvement

  13. Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting

    Oct 21, 2026Zhipeng Chen, Yunsen Liang, Yanxi Chen +12Recursive Self-ImprovementSelf-Evolving Agents

  14. From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation

    Oct 21, 2026Tingwen Du, Haoyu Guo, Hanxue Zhang +9Robotic ManipulationLong-Horizon Robotic Manipulation

  15. VeriEvolve: Evaluator-First Evolution for Tool-Using Agents

    Oct 21, 2026Yueshen Li, Kamer Ali Yuksel, Gokhan Tur +2Self-Evolving AgentsTool-Use Evaluation

  16. Evolving Agent Interfaces

    Oct 20, 2026Saaket Agashe, Yuzhe Yang, Gonzalo Gonzalez-Pumariega +5Computer-Use AgentsSelf-Evolving Agents

  17. KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses

    Oct 20, 2026Zhikang Chen, Yueqing Sun, Sen Cui +6Agent Harness OptimizationLong-Horizon Agent Tasks

  18. Are Self-Evolving Agents Continual Learners?

    Oct 19, 2026Xiaoyin Chen, Yizheng Huang, Yinglun Xu +4Continual Learning for LLM AgentsSelf-Evolving Agents

  19. ACE-Trader: Adversarial Co-Evolution for Generator-Critic Trading Systems

    Oct 19, 2026Chang Zhou, Jiarun Zhou, Xingtong Yu +3Algorithmic TradingMemory-Augmented Agents

  20. Memory as Belief: Bayesian Evolution of Memory for Self-Evolving LLM Agents

    Oct 18, 2026Yiming Xu, Qian Yang, Zihan Chen +4Memory Management for LLM AgentsSelf-Evolving Agents

  21. Selm: Self-Evolving Library Management for Multi-Skill Agent Optimization

    Oct 17, 2026Mengxi Hu, Yuxuan Hu, Jinbo Su +6LLM Agent Skill LearningLLM Agents

  22. DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery

    Oct 16, 2026Yuxing Chen, Zhisheng Zhang, Cheng Tang +20LLM Agent HarnessesDrug Discovery

  23. Darwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving Agents

    Oct 16, 2026Mingze Yin, Xiaohan Wang, Dian Li +4Self-Evolving AgentsContinual Learning for LLM Agents

  24. LLM Evolution in a Simple Simulated Market

    Oct 16, 2026Charlie Pilgrim, Christopher Krupenye, Dora Biro +1Emergent Misalignment in Language ModelsSelf-Evolving Agents

  25. Self-Evolving Agents Can Repair Failures but Struggle to Generalize from Them

    Oct 16, 2026Weixiang Zhao, Yichen Zhang, Yanyan Zhao +5LLM Agent Self-ImprovementSelf-Evolving Agents

  26. Self-Evolving Coding Agents via Harness-Policy Optimization

    Oct 16, 2026Zhepei Wei, Wenlin Yao, Baolin Peng +5AI Coding AgentsAgent Harness Optimization