mlsanityData to 7 Oct 2026

A Survey on Self-Evolution of Large Language Models

arXiv 2404.14387 ↗First posted 22 Apr 2024cs.CL cs.AIcited by 86

Not on the map. Why?

Cited by 34 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. However, current LLMs that learn from human or external model supervision are costly and may face performance ceilings as task complexity and diversity increase. To address this issue, self-evolution approaches that enable LLM to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing. This new training paradigm inspired by the human experiential learning process offers the potential to scale LLMs towards superintelligence. In this work, we present a comprehensive survey of self-evolution approaches in LLMs. We first propose a conceptual framework for self-evolution and outline the evolving process as iterative cycles composed of four phases: experience acquisition, experience refinement, updating, and evaluation. Second, we categorize the evolution objectives of LLMs and LLM-based agents; then, we summarize the literature and provide taxonomy and insights for each module. Lastly, we pinpoint existing challenges and propose future directions to improve self-evolution frameworks, equipping researchers with critical insights to fast-track the development of self-evolving LLMs. Our corresponding GitHub repository is available at https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/Awesome-Self-Evolution-of-LLM

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). Builds on 122 of its 152 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

122 of 152 references.

References · 122

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  7. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  8. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  9. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  10. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  11. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  12. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
38 more
  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  2. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  4. 2023Qwen Technical Reportcited by 3,273
  5. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  7. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  8. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  9. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  10. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  12. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  13. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  14. 2023LIMA: Less Is More for Alignmentcited by 1,080
  15. 2022Red Teaming Language Models with Language Modelscited by 983
  16. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  17. 2023Teaching Large Language Models to Self-Debugcited by 963
  18. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  19. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  20. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 795
  21. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  22. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  23. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  24. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  25. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  26. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
  27. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  28. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 679
  29. 2022Large Language Models Can Self-Improvecited by 656
  30. 2024Self-Rewarding Language Modelscited by 654
  31. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  32. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  33. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 486
  34. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  35. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  36. 2022Self-critiquing models for assisting human evaluatorscited by 372
  37. 2023Language Models can Solve Computer Taskscited by 371
  38. 2022CodeT: Code Generation with Generated Testscited by 369

50 most cited of 122 All 122 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 30; 2026: 42.

86 papers.

Sort:

By area:

  1. 2025R-Zero: Self-Evolving Reasoning LLM from Zero Datacited by 210
  2. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  3. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
  4. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  5. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 128
  6. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
  7. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 105
  8. 2025UI-Venus Technical Report: Building High-performance UI Agents with RFTcited by 90
  9. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Taskscited by 83
  10. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  11. 2025AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progresscited by 69
  12. 2025Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoningcited by 68
38 more
  1. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  2. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  3. 2024MMEvol: Empowering Multimodal Large Language Models with Evol-Instructcited by 42
  4. 2024Preference Optimization for Reasoning with Pseudo Feedbackcited by 38
  5. 2024OSCAR: Operating System Control via State-Aware Reasoning and Re-Planningcited by 37
  6. 2025Guided Self-Evolving LLMs with Minimal Human Supervisioncited by 33
  7. 2024Automated Proof Generation for Rust Code via Self-Evolutioncited by 31
  8. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 29
  9. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  10. 2024Configurable Foundation Models: Building LLMs from a Modular Perspectivecited by 22
  11. 2025Revisit Self-Debugging with Self-Generated Tests for Code Generationcited by 21
  12. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 19
  13. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Lawcited by 18
  14. 2025AI for Service: Proactive Assistance with AI Glassescited by 18
  15. 2025Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learningcited by 17
  16. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  17. 2025Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimizationcited by 16
  18. 2025A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loopscited by 15
  19. 2026G-Zero: Self-Play for Open-Ended Generation from Zero Datacited by 15
  20. 2024Towards LifeSpan Cognitive Systemscited by 13
  21. 2025Truly Self-Improving Agents Require Intrinsic Metacognitive Learningcited by 13
  22. 2025Escaping Collapse: The Strength of Weak Data for Large Language Model Trainingcited by 11
  23. 2025OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesiscited by 10
  24. 2025Alita-G: Self-Evolving Generative Agent for Agent Generationcited by 10
  25. 2024Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approachcited by 9
  26. 2026R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Trainingcited by 9
  27. 2024Towards Building Specialized Generalist AI with System 1 and System 2 Fusioncited by 8
  28. 2025BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systemscited by 8
  29. 2025Writing as a testbed for open ended agentscited by 8
  30. 2026Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studiescited by 6
  31. 2026Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skillscited by 6
  32. 2025Entropy-Based Adaptive Weighting for Self-Trainingcited by 5
  33. 2026Self-Improvement of Large Language Models: A Technical Overview and Future Outlookcited by 5
  34. 2026The Last AI Built by Humans: Toward Genuine Recursive Self-Improvementcited by 5
  35. 2024ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictionscited by 4
  36. 2026Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Taskscited by 4
  37. 2026SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environmentscited by 4
  38. 2026Rethinking Continual Experience Internalization for Self-Evolving LLM Agentscited by 4

50 most cited of 86 All 86 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Self-Consolidation for Self-Evolving Agents
  2. 2025The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
  3. 2026Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
  4. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
  5. 2026Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination
  6. 2026When Is Enough Enough in Self-Evolving LLM Systems?
  7. 2024Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation
  8. 2026Position: Agentic Evolution is the Path to Evolving LLMs