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 Feedback-Free Self-Evolution Reshapes Agent Skills: A Systematic Study

    Nov 19, 2026Litao Guo, Man Chen, Xinli Xu +3LLM Agent Skill LearningSelf-Evolving Agents

  2. Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills

    Nov 19, 2026Boyin Tan, Jiadong Zhang, Xiaosong Ma +3LLM Agent Skill LearningSelf-Evolving Agents

  3. Space-X: Self-Evolving Spatial Agents Weaving Clues into Evidence Chains

    Nov 18, 2026Zijian Zhang, Wenqing Tian, Qiang Liu +1Spatial Reasoning in Language ModelsEvidence-Grounded Reasoning

  4. EvoSkill-S1: Evolving Reusable Skills with Genetic-Inspired Operators

    Nov 17, 2026Yujun Wang, Jiqiang Li, Yinuo Lu +10LLM Agent Skill LearningSelf-Evolving Agents

  5. EvoDisco: Strategy Discovery for Evolving Agent Memory

    Nov 17, 2026Mingyang Liu, Qingcan Kang, Shixiong Kai +4Memory Management for LLM AgentsMemory Consolidation for LLM Agents

  6. MetaAct: Self-Evolving Executable Action Constraints for Embodied Language Agents

    Nov 16, 2026Jiaxing Zhao, Hanwen Wang, Di Liu +9Self-Evolving AgentsEmbodied AI

  7. When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization

    Nov 7, 2026Minhua Lin, Zongyu Wu, Hanqing Lu +4LLM Backdoor AttacksBackdoor Attacks

  8. Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI

    Nov 4, 2026Andrew W. Lo, Chaoyi ZhaoSelf-Evolving AgentsAI Safety

  9. EvoGuard: Mitigating Degradation in Online Skill Evolution

    Nov 4, 2026Yanli Wang, Zichen Bai, Tianyue Jiang +12LLM Agent Skill LearningSelf-Evolving Agents

  10. Artifact-to-Capability: Diagnosing Breaks in Capability Formation of Self-Evolving Agents in a Controlled Environment

    Nov 3, 2026Ziqian Ban, Haoxiang Yang, Yanfei Zhang +6Self-Evolving AgentsProcess-Based Agent Evaluation

  11. Goal-Driven Autonomous Optical Experimentation via a Self-Recursive Hardware-Software Harness

    Nov 3, 2026Tianxing Zhu, Huacheng Lu, Ming Liu +1Autonomous ExperimentationAutonomous Research Agents

  12. EvoGroup: A Self-Evolving Harness for Group Agents in Shared Contexts

    Nov 2, 2026Xinyi Xu, Xiaoyang Li, Yucheng Feng +5Agent Harness Self-EvolutionSelf-Evolving Agents

  13. Networked AI: Architecture, Theory, and Applications

    Nov 2, 2026Liang Song, Jiayue Jin, Peng Sun +9AI Agent ArchitectureMulti-Agent Systems

  14. Automated Stateful Specialization for Adaptive Agent Systems

    Nov 1, 2026Myan Vu, Harrish Ayyanar, Jiang Pang +2Self-Evolving AgentsAgent Skill Learning

  15. 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

  16. A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development

    Nov 1, 2026Leming Shen, Qiang Yang, Xinyu Huang +3AI Coding AgentsSelf-Evolving Agents

  17. Learning to Interact and Direct: Co-Evolving Video Director Agents

    Oct 30, 2026Yingzhao Jian, Zhongan Wang, Yuxuan Hou +1Agentic Video GenerationSelf-Evolving Agents

  18. EvoMCP: Co-evolving MCP agents and training data

    Oct 30, 2026Xuanang Gao, Kepeng Lin, Xinyan Shi +6LLM Agent TrainingTool-Using Agents

  19. More Rules, Longer Lists? Benchmarking Self-Evolving Agents on a Hidden-Rule Curriculum

    Oct 29, 2026Chenjie Qiu, Boyan Xu, Shaobin Shi +3Self-Evolving AgentsAI Agent Benchmarks

  20. EvoTeam: Multi-Agent Collaboration via Evolving Teams

    Oct 29, 2026Qinuo Cao, Xin He, Dianxuan Fu +7Multi-Agent CollaborationMulti-Agent Systems

  21. Compile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation

    Oct 29, 2026Chengyu Yang, Yunxiang Zheng, Zongzheng Li +6LLM Agent Skill LearningSelf-Evolving Agents

  22. Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection

    Oct 29, 2026Xinyan Wang, Xiaogeng Liu, Jun Shao +1AI Agent SecurityAI Agent Safety

  23. MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems

    Oct 28, 2026Hehai Lin, Qi Yang, Chengwei QinMulti-Agent OrchestrationMulti-Agent System Optimization

  24. Evolving Agent Teams

    Oct 27, 2026Shiyi Cao, Ziming Mao, Dacheng Li +2Multi-Agent CodingSelf-Evolving Agents

  25. Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security

    Oct 26, 2026Leo Benaharon, Chi Zhang, Wei Zheng +3Robot Policy AdaptationSelf-Evolving Agents