mlsanityData to 7 Oct 2026

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

arXiv 2603.01145 ↗First posted 1 Mar 2026cs.AIcited by 105

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

In practical LLM applications, users repeatedly express stable preferences and requirements, such as reducing hallucinations, following institutional writing conventions, or avoiding overly technical wording, yet such interaction experience is seldom consolidated into reusable knowledge. Consequently, LLM agents often fail to accumulate personalized capabilities across sessions. We present AutoSkill, an experience-driven lifelong learning framework that enables LLM agents to automatically derive, maintain, and reuse skills from dialogue and interaction traces. AutoSkill abstracts skills from user experience, supports their continual self-evolution, and dynamically injects relevant skills into future requests without retraining the underlying model. Designed as a model-agnostic plugin layer, it is compatible with existing LLMs and introduces a standardized skill representation for sharing and transfer across agents, users, and tasks. In this way, AutoSkill turns ephemeral interaction experience into explicit, reusable, and composable capabilities. This paper describes the motivation, architecture, skill lifecycle, and implementation of AutoSkill, and positions it with respect to prior work on memory, retrieval, personalization, and agentic systems. AutoSkill highlights a practical and scalable path toward lifelong personalized agents and personal digital surrogates.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 42 of its 47 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

42 of 47 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  2. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  3. 2025MemInsight: Autonomous Memory Augmentation for LLM Agents27 Mar
  4. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  5. 2025Lifelong Learning of Large Language Model based Agents: A Roadmap13 Jan
  6. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  7. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  11. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  12. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
23 more
  1. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  2. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  3. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  4. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  6. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  7. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  8. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  9. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  11. 2022Large Language Models Can Self-Improvecited by 656
  12. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  13. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  14. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  15. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  16. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  17. 2023ART: Automatic multi-step reasoning and tool-use for large language modelscited by 193
  18. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 162
  19. 2025Self-Evolving Curriculum for LLM Reasoningcited by 107
  20. 2024A Survey on Self-Evolution of Large Language Modelscited by 86
  21. 2025Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmarkcited by 43
  22. 2023SELF: Self-Evolution with Language Feedbackcited by 24
  23. 2024Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimizationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 105.

105 papers.

Sort:

By area:

  1. 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skillscited by 122
  2. 2026CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verificationcited by 117
  3. 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolvercited by 76
  4. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  5. 2026SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Taskscited by 45
  6. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  7. 2026SkillGen: Verified Inference-Time Agent Skill Synthesiscited by 29
  8. 2026Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learningcited by 28
  9. 2026Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agentscited by 28
  10. 2026MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluationcited by 23
  11. 2026SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revisioncited by 21
  12. 2026SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agentscited by 19
38 more
  1. 2026From Context to Skills: Can Language Models Learn from Context Skillfully?cited by 19
  2. 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolutioncited by 18
  3. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  4. 2026Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agentscited by 16
  5. 2026MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolutioncited by 12
  6. 2026SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditingcited by 11
  7. 2026Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Librariescited by 10
  8. 2026OpenSkill: Open-World Self-Evolution for LLM Agentscited by 9
  9. 2026SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topologycited by 8
  10. 2026Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluationcited by 8
  11. 2026EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfercited by 8
  12. 2026ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimizationcited by 6
  13. 2026From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?cited by 6
  14. 2026SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agentscited by 6
  15. 2026SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestrationcited by 6
  16. 2026CODESKILL: Learning Self-Evolving Skills for Coding Agentscited by 6
  17. 2026Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Librariescited by 6
  18. 2026Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?cited by 6
  19. 2026SkillsInjector: Dynamic Skill Context Construction for LLM Agentscited by 5
  20. 2026VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generationcited by 5
  21. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 5
  22. 2026SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agentscited by 5
  23. 2026Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agentscited by 4
  24. 2026ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillationcited by 4
  25. 2026OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agentscited by 4
  26. 2026Mem-π: Adaptive Memory through Learning When and What to Generatecited by 3
  27. 2026Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?cited by 3
  28. 2026SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skillscited by 3
  29. 2026Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Languagecited by 2
  30. 2026Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolutioncited by 2
  31. 2026OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillationcited by 2
  32. 2026Exploring Autonomous Agentic Data Engineering for Model Specializationcited by 2
  33. 2026EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Managementcited by 2
  34. 2026VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agentscited by 2
  35. 2026Unsupervised Skill Discovery for Agentic Data Analysiscited by 2
  36. 2026RedAct: Redacting Agent Capability Traces for Procedural Skill Protectioncited by 2
  37. 2026SkillWiki: A Living Knowledge Infrastructure for Agent Skillscited by 2
  38. 2026OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Modelscited by 2

50 most cited of 105 All 105 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
  2. 2025LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
  3. 2026Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents
  4. 2024Self-Evolving GPT: A Lifelong Autonomous Experiential Learner
  5. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles
  6. 2026Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
  7. 2025Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
  8. 2026Memento-Skills: Let Agents Design Agents