WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally bene

\uselogo Cyrus Rashtchian Affiliation: Google Research Chun-Sung Ferng Affiliation: Google Research Andrew Tomkins Affiliation: Google Research Da-Cheng Juan Affiliation: Google Research Tu Vu Corresponding author: lytang@google.com, ttvu@google.com Affiliation: Google Research Affiliation: Virginia Tech Abstract Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the…

saved by

• Emma Guo

related reading

• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• llm-wikigist.github.com
• A Steerable Model with Emergent Capabilitiespi.website
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• Meta Context Engineering via Agentic Skill Evolutionarxiv.org
• Self-Adapting Language Modelsarxiv.org
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
• The Agent Skills Directoryskills.sh
• GitHub - nashsu/llm_wiki: LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。github.com
• Scaling Activation Oracles to Trillion-Parameter Modelstransluce.org
• The Agent Skills Directoryskills.sh
• Agent Skills Overview - Agent Skillsagentskills.io