mlsanityData to 7 Oct 2026

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills

arXiv 2504.07079 ↗First posted 9 Apr 2025cs.AI cs.CL cs.CVcited by 174

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

To survive and thrive in complex environments, humans have evolved sophisticated self-improvement mechanisms through environment exploration, hierarchical abstraction of experiences into reuseable skills, and collaborative construction of an ever-growing skill repertoire. Despite recent advancements, autonomous web agents still lack crucial self-improvement capabilities, struggling with procedural knowledge abstraction, refining skills, and skill composition. In this work, we introduce SkillWeaver, a skill-centric framework enabling agents to self-improve by autonomously synthesizing reusable skills as APIs. Given a new website, the agent autonomously discovers skills, executes them for practice, and distills practice experiences into robust APIs. Iterative exploration continually expands a library of lightweight, plug-and-play APIs, significantly enhancing the agent's capabilities. Experiments on WebArena and real-world websites demonstrate the efficacy of SkillWeaver, achieving relative success rate improvements of 31.8% and 39.8%, respectively. Additionally, APIs synthesized by strong agents substantially enhance weaker agents through transferable skills, yielding improvements of up to 54.3% on WebArena. These results demonstrate the effectiveness of honing diverse website interactions into APIs, which can be seamlessly shared among various web agents.

Key facts. Cited by 174 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 53 of its 82 references that are in the map. First posted on arXiv 9 Apr 2025.

Builds on

53 of 82 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025An Illusion of Progress? Assessing the Current State of Web Agents2 Apr
  2. 2025Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents17 Feb
  3. 2024Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents17 Dec
  4. 2024ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data22 Nov
  5. 2024Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents10 Nov
  6. 2024Beyond Browsing: API-Based Web Agents21 Oct
  7. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation17 Oct
  8. 2024Agent Workflow Memory11 Sep
  9. 2024AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?22 Jul
  10. 2024Large Language Models Can Self-Improve At Web Agent Tasks30 May
  11. 2024WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models25 Jan
  12. 2024GPT-4V(ision) is a Generalist Web Agent, if Grounded3 Jan
3 more
  1. 2023WebArena: A Realistic Web Environment for Building Autonomous Agents25 Jul
  2. 2023Mind2Web: Towards a Generalist Agent for the Web9 Jun
  3. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents4 Jul

Other references · 38

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  6. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  7. 2023CogAgent: A Visual Language Model for GUI Agentscited by 692
  8. 2022Large Language Models Can Self-Improvecited by 656
  9. 2024Self-Rewarding Language Modelscited by 654
  10. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 553
  11. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  12. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
26 more
  1. 2024Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agentscited by 373
  2. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  3. 2023Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Modelscited by 325
  4. 2023Large Language Models as Tool Makerscited by 293
  5. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 223
  6. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  7. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 201
  8. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  9. 2024On the Effects of Data Scale on UI Control Agentscited by 187
  10. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 185
  11. 2024Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMscited by 173
  12. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 159
  13. 2024Tree Search for Language Model Agentscited by 148
  14. 2024Autonomous Evaluation and Refinement of Digital Agentscited by 136
  15. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 122
  16. 2023LEGO-Prover: Neural Theorem Proving with Growing Librariescited by 108
  17. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Explorationcited by 100
  18. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 93
  19. 2023CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Modelscited by 90
  20. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 70
  21. 2023From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfacescited by 67
  22. 2023SteP: Stacked LLM Policies for Web Actionscited by 66
  23. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  24. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
  25. 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Languagecited by 34
  26. 2025Training a Generally Curious Agentcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 34; 2026: 140.

174 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2026Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skillscited by 161
  3. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  4. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 99
  5. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 91
  6. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  7. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  8. 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolvercited by 76
  9. 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 71
  10. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
  11. 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skillscited by 53
  12. 2025Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agentscited by 52
38 more
  1. 2026SkillNet: Create, Evaluate, and Connect AI Skillscited by 48
  2. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  3. 2026SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Taskscited by 45
  4. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  5. 2025DeepShop: A Benchmark for Deep Research Shopping Agentscited by 42
  6. 2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interactioncited by 34
  7. 2025CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolutioncited by 33
  8. 2025Go-Browse: Training Web Agents with Structured Explorationcited by 32
  9. 2025VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelscited by 31
  10. 2026SkillGen: Verified Inference-Time Agent Skill Synthesiscited by 29
  11. 2025PolySkill: Learning Generalizable Skills Through Polymorphic Abstractioncited by 25
  12. 2025Accumulating Context Changes the Beliefs of Language Modelscited by 25
  13. 2026GraSP: Graph-Structured Skill Compositions for LLM Agentscited by 25
  14. 2026WebXSkill: Skill Learning for Autonomous Web Agentscited by 24
  15. 2026ReCreate: Reasoning and Creating Domain Agents Driven by Experiencecited by 22
  16. 2026SkillTrojan: Backdoor Attacks on Skill-Based Agent Systemscited by 21
  17. 2025WebGuard: Building a Generalizable Guardrail for Web Agentscited by 20
  18. 2025Improving Code Localization with Repository Memorycited by 19
  19. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 19
  20. 2026SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agentscited by 19
  21. 2026From Context to Skills: Can Language Models Learn from Context Skillfully?cited by 19
  22. 2025Build the web for agents, not agents for the webcited by 17
  23. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  24. 2026SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystemscited by 17
  25. 2026SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agentscited by 17
  26. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  27. 2026Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agentscited by 16
  28. 2025WALT: Web Agents that Learn Toolscited by 15
  29. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 15
  30. 2026SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfacescited by 15
  31. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspectivecited by 14
  32. 2026ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agentscited by 13
  33. 2026MMSkills: Towards Multimodal Skills for General Visual Agentscited by 13
  34. 2026ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RLcited by 13
  35. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  36. 2026Skill-R1: Agent Skill Evolution via Reinforcement Learningcited by 12
  37. 2026MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolutioncited by 12
  38. 2025Automated Skill Discovery for Language Agents through Exploration and Iterative Feedbackcited by 11

50 most cited of 174 All 174 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction
  2. 2025Inducing Programmatic Skills for Agentic Tasks
  3. 2026MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
  4. 2026Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
  5. 2026Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
  6. 2026SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
  7. 2026SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
  8. 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution