WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Summary
WikiSkill introduces a framework that co-evolves agent skills with a persistent knowledge base to systematically accumulate experience and improve performance across models, demonstrating benefits over state-of-the-art skill-evolution methods.
View Cached Full Text
Cached at: 08/28/26, 03:24 AM
Paper page - WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Source: https://huggingface.co/papers/2608.27454
Abstract
WikiSkill co-evolves reusable agent skills with a persistent knowledge base to systematically accumulate experience and improve performance across models.
Agent skillspackage 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 introduceWikiSkill, a framework that co-evolvesagent skillswith apersistent knowledge base(wiki). At a high level,WikiSkillseparates 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,WikiSkillconsistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find thatskill evolutioncomplements model scaling: larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them. We also find that evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills. Finally, ourablation studiesconfirm that persistent knowledge accumulation in the wiki is critical for effectiveskill evolution. These results demonstrate the benefits of systematically accumulating and refining agent experience for developing reusable and transferable skills.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2608\.27454
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.27454 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.27454 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.27454 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Google Introduces WikiSkill for Persistent Agent Learning (22 minute read)
WikiSkill is a framework that co-evolves agent skills with a persistent knowledge base, consistently outperforming state-of-the-art methods and enabling effective skill transfer across models.
@omarsar0: A great paper from Google on maintaining agent skills through persistent knowledge.
A Google paper discusses maintaining agent skills by separating raw execution traces from persistent knowledge in a wiki-like structure.
A preprint says smaller models with evolved skills can beat larger models without them. What should persist?
WikiSkill uses a persistent wiki to evolve and transfer skills, showing that smaller models with such skills can outperform larger models without them in benchmarks, raising questions about what knowledge should persist in AI agents.
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Skill1 is a unified framework that trains a single policy to co-evolve skill selection, utilization, and distillation using a shared task-outcome objective. Experiments on ALFWorld and WebShop show it outperforms existing baselines in complex task environments.
SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
SkillForge proposes an agentic reinforcement learning method that co-evolves an LLM agent and its skill library through a fitness-driven lifecycle of trial, active, stable, and retired states. It reports up to 7.8% relative improvement over strong baselines on interactive agent benchmarks and releases SkillFurnace, a 5k+ record dataset for studying skill quality and lifecycle management.