MASkills: Continual Skills Optimization for Multi-Agent LLM Systems

2026-09-02

AI Summary

本文提出MASkills框架，通过优化代理技能解决多代理LLM系统中持续改进的问题，实验表明其在多个任务中的有效性。

Abstract

LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging. Existing self-reflection methods build experience memories, but memories are mostly hard to invoke, refine, or scale, while agent skills offer a more actionable unit: structured procedural knowledge that specifies when to act, how to act, and which resources or tools to use. We introduce MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills. MASkills presents a new agent-optimization pipeline that integrates skill-conditioned credit assignment, hierarchical credit aggregation, and momentum-smoothed optimization, enabling agent skill libraries to evolve through refinement, induction, consolidation, and pruning. Experiments on HotpotQA, LoCoMo, and GAIA demonstrate the effectiveness of MASkills across multiple agentic tasks. Our code is available at https://github.com/DaRL-GenAI/MASkills

Problem

• Continual Improvement
• Multi-Agent LLM Systems
• Experience Memories
• Agent Skills

Innovation

• Continual Learning
• Multi-Agent LLM Systems
• Skill-Conditioned Credit Assignment
• Hierarchical Credit Aggregation
• Momentum-Smoothed Optimization