SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

2026-04-09

AI Summary

Current large language model agents exhibit static skill sets after deployment and struggle to continuously learn from interactions with multiple users, leading to redundant exploration and inefficiency. This work proposes SkillClaw, a framework that enables collective skill evolution within a multi-user agent ecosystem for the first time. By aggregating interaction trajectories across users and time, SkillClaw employs an autonomous evolver based on trajectory clustering and behavioral pattern mining to automatically refine or expand skills, which are then synchronized into a shared skill library. This mechanism facilitates cross-scenario knowledge transfer and system-level capability accumulation without human intervention. Evaluated on the WildClawBench benchmark, SkillClaw significantly enhances the performance of Qwen3-Max on real-world agent tasks with only minimal user interaction.

Abstract

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.

Problem

• skill evolution
• multi-user agent
• collective learning
• LLM agents
• experience aggregation

Innovation

• collective skill evolution
• agentic evolver
• multi-user agent ecosystem
• skill repository
• cross-user knowledge transfer