SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Papers with Code Trending Papers

Summary

SkillClaw introduces a framework for collective skill evolution in multi-user LLM agent systems, enabling autonomous updates and cross-user knowledge transfer by aggregating interactions and feedback to improve performance across the ecosystem.

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for improving skills. SkillClaw continuously aggregates trajectories generated during use and processes them with an autonomous evolver, which identifies recurring behavioral patterns and translates them into updates to the skill set by refining existing skills or extending them with new capabilities. The resulting skills are maintained in a shared repository and synchronized across users, allowing improvements discovered in one context to propagate system-wide while requiring no additional effort from users. By integrating multi-user experience into ongoing skill updates, SkillClaw enables cross-user knowledge transfer and cumulative capability improvement, and experiments on WildClawBench show that limited interaction and feedback, it significantly improves the performance of Qwen3-Max in real-world agent scenarios.
Original Article
View Cached Full Text

Cached at: 06/08/26, 09:15 AM

Paper page - SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Source: https://huggingface.co/papers/2604.08377

Abstract

SkillClaw enables collective skill evolution in multi-user LLM agent systems by aggregating user interactions to autonomously update and improve reusable skills across the ecosystem.

Large language model (LLM) agents such as OpenClaw rely onreusable skillsto perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution inmulti-user agent ecosystems, which treats cross-user and over-time interactions as the primary signal for improving skills. SkillClaw continuously aggregates trajectories generated during use and processes them with anautonomous evolver, which identifies recurring behavioral patterns and translates them into updates to the skill set by refining existing skills or extending them with new capabilities. The resulting skills are maintained in ashared repositoryand synchronized across users, allowing improvements discovered in one context to propagate system-wide while requiring no additional effort from users. By integrating multi-user experience into ongoing skill updates, SkillClaw enablescross-user knowledge transferandcumulative capability improvement, and experiments on WildClawBench show that limited interaction and feedback, it significantly improves the performance of Qwen3-Max in real-world agent scenarios.

View arXiv pageView PDFGitHub1.73kAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2604.08377 in a model README.md to link it from this page.

Datasets citing this paper1

#### zhongweixie/A-Survey-on-AI-Agent-Harness Viewer• Updated18 days ago • 1 • 160 • 1

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2604.08377 in a Space README.md to link it from this page.

Collections including this paper21

Browse 21 collections that include this paper

Similar Articles

OpenSkill: Open-World Self-Evolution for LLM Agents

Hugging Face Daily Papers

OpenSkill is a framework for LLM agents to self-evolve skills and verification signals from open-world resources without target-task supervision, achieving high performance across benchmarks.

SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration

arXiv cs.AI

SkillFlow proposes a flow-driven recursive skill evolution framework for LLM-based agentic orchestration, using Tempered Trajectory Balance to prevent strategy collapse and provide transparent credit assignment. Experiments on 14 datasets show significant improvements over baselines in QA, math, code, and decision-making tasks.