mlsanityData to 14 Oct 2026

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

arXiv 2508.07407 ↗First posted 10 Aug 2025cs.AI cs.CL cs.MAcited by 183

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

also in 1 more
Abstract (arXiv)

Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after deployment, limiting their ability to adapt to dynamic and evolving environments. To this end, recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback. This emerging direction lays the foundation for self-evolving AI agents, which bridge the static capabilities of foundation models with the continuous adaptability required by lifelong agentic systems. In this survey, we provide a comprehensive review of existing techniques for self-evolving agentic systems. Specifically, we first introduce a unified conceptual framework that abstracts the feedback loop underlying the design of self-evolving agentic systems. The framework highlights four key components: System Inputs, Agent System, Environment, and Optimisers, serving as a foundation for understanding and comparing different strategies. Based on this framework, we systematically review a wide range of self-evolving techniques that target different components of the agent system. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where optimisation objectives are tightly coupled with domain constraints. In addition, we provide a dedicated discussion on the evaluation, safety, and ethical considerations for self-evolving agentic systems, which are critical to ensuring their effectiveness and reliability. This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents, laying the foundation for the development of more adaptive, autonomous, and lifelong agentic systems.

Key facts. Cited by 183 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. First posted on arXiv 10 Aug 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 36; 2026: 147.

183 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 95
  3. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 76
  4. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutioncited by 73
  5. 2026How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settingscited by 65
  6. 2025Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agentscited by 62
  7. 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 55
  8. 2025Barbarians at the Gate: How AI is Upending Systems Researchcited by 54
  9. 2025FLEX: Continuous Agent Evolution via Forward Learning from Experiencecited by 52
  10. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  11. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 49
  12. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 49
38 more
  1. 2025EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systemscited by 37
  2. 2026Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharingcited by 36
  3. 2025VISTA: A Test-Time Self-Improving Video Generation Agentcited by 31
  4. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 29
  5. 2025StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Modelscited by 26
  6. 2026EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selectioncited by 24
  7. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  8. 2026RealMem: Benchmarking LLMs in Real-World Memory-Driven Interactioncited by 20
  9. 2026Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updatescited by 19
  10. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  11. 2026Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?cited by 18
  12. 2025AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agentcited by 17
  13. 2026Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gaincited by 17
  14. 2026SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learningcited by 17
  15. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspectivecited by 17
  16. 2026QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Miningcited by 16
  17. 2026On Safety Risks in Experience-Driven Self-Evolving Agentscited by 14
  18. 2026OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiencescited by 14
  19. 2025Agentic Learner with Grow-and-Refine Multimodal Semantic Memorycited by 13
  20. 2026EnvHarness: Awakening Static Worlds for Agent Learningcited by 13
  21. 2026Controlled Self-Evolution for Algorithmic Code Optimizationcited by 12
  22. 2026Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillationcited by 12
  23. 2025AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoningcited by 11
  24. 2026SEAGym: An Evaluation Environment for Self-Evolving LLM Agentscited by 11
  25. 2026The Last AI Built by Humans: Toward Genuine Recursive Self-Improvementcited by 11
  26. 2025Interactive Recommendation Agent with Active User Commandscited by 10
  27. 2025Alita-G: Self-Evolving Generative Agent for Agent Generationcited by 10
  28. 2026R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Trainingcited by 10
  29. 2025LatentEvolve: Self-Evolving Test-Time Scaling in Latent Spacecited by 9
  30. 2026PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agentscited by 9
  31. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  32. 2025BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Webcited by 7
  33. 2025Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Railscited by 7
  34. 2025Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systemscited by 7
  35. 2026ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Webcited by 7
  36. 2026The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societiescited by 7
  37. 2026Safety in Embodied AI: A Survey of Risks, Attacks, and Defensescited by 7
  38. 2025An Evaluation-Centric Paradigm for Scientific Visualization Agentscited by 6

50 most cited of 183 All 183 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
  2. 2025AI Agents: Evolution, Architecture, and Real-World Applications
  3. 2024A Survey on Self-Evolution of Large Language Models
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
  5. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond
  6. 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
  7. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  8. 2026Self-Evolving AI for Humanoids: Mechanisms, Safety, and Evaluation of Post-Deployment Self-Improvement