WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

ArticleLiyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu VuResearch

This research paper introduces WikiSkill, a framework that co-evolves AI agent skills alongside a persistent knowledge base (wiki). By disentangling raw execution experience, accumulated knowledge, and executable skills, WikiSkill enables systematic reuse of insights across iterations.

Key points

  1. WikiSkill decouples raw execution traces, accumulated knowledge in a wiki, and executable skills.
  2. Interaction experience is continuously consolidated into the wiki, providing a persistent foundation for subsequent skill updates.
  3. The framework outperforms state-of-the-art skill evolution methods across diverse benchmarks and model families.
  4. Skill evolution complements scaling: smaller models equipped with evolved skills can outperform substantially larger models lacking them.
  5. Evolved skills transfer effectively across different models, with skills developed by one model sometimes outperforming self-evolved skills.
  6. Ablation studies confirm that persistent knowledge accumulation in the wiki is the critical driver of performance gains.

Why it matters

Autonomous agents often lose valuable operational insights because optimization histories remain scattered and ephemeral. Structuring knowledge into a persistent, evolving wiki allows agents to build modular expertise that can be shared across models and tasks.

Analysis

The paper provides an architectural blueprint for sustainable agent learning. The finding that cross-model transfer works effectively—and that smaller models can surpass larger baselines when equipped with evolved skills—offers practical efficiency benefits for deploying specialized agent workflows.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Siru Ouyang, Jun Yan, I-Hung Hsu, et al.

    ReasoningBank: Scaling Agent Self-Evolution with Reasoning Memory

    ReasoningBank is a memory framework for LLM agents that distils generalisable reasoning strategies from self-judged successful and failed experiences, enabling continuous self-evolution over time.

    AI & LLMs· Research

  • Article:Hongjun Liu, Yifei Ming, Shafiq Joty, Chen Zhao

    HASP: Harnessing LLM Agents with Executable Skill Programs

    A research team introduces HASP (Harnessing LLM Agents with Skill Programs), a framework that converts past agent experiences into executable Program Functions (PFs). Instead of relying on passive textual prompts, PFs act as executable guardrails that trigger on failure-prone states to alter the next action or supply corrective context.

    AI & LLMs· Research

  • Article:Devansh

    Stateful Swarms: How Persistent Memory Outperforms Traditional Agent Architectures

    Devansh explores 'Stateful Swarms', an architecture tackling volatile contexts and repetitive document processing through a persistent blackboard state. Instead of repeatedly processing large inputs or losing signal across conversational handoffs, specialized agents populate an append-only, structured memory. Evaluated on the Harvey Legal Agent Benchmark, this setup yielded higher task pass rates at significantly lower operational costs.

    AI & LLMs· Opinion

  • Article:Shuai Shao, Kangning Zhang, Qingyao Li, Shijian Wang, Hao Wang, Wenxiang Jiao, Yuan Lu, Yi Guo, Weiwen Liu, Weinan Zhang

    Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

    Researchers introduce Harness-R1, a framework that trains a dedicated agent to adapt and patch the runtime harness of LLM agents based on failure logs. Using online reinforcement learning, a separate 9B model learns to generate executable patches for context handling, tool mediation, and error recovery to directly improve task completion.

    AI & LLMs· Research

  • Link:Anthropic

    Agent Skills: An Open Standard for Modular AI Agent Capabilities

    Agent Skills is an open format designed to equip AI agents with specialised domain knowledge and repeatable workflows. Centred around a directory containing a SKILL.md file, it relies on progressive disclosure to keep context overhead minimal.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.