让多智能体LLM系统持续优化技能，提升复杂任务表现
MASkills: Continual Skills Optimization for Multi-Agent LLM Systems
- 以技能为单位进行持续学习，明确何时、如何、用什么工具行动
- 在多个数据集上实现性能提升，最高达12.7%的准确率改进
- 适合需要长期进化能力的多智能体系统研究者
基于大模型的多智能体系统在复杂任务中表现强劲，但持续从交互经验中学习仍具挑战。现有自省方法虽构建经验记忆，但记忆难以调用、精炼或扩展；而智能体技能作为更可操作的单元——结构化过程知识，明确了行动时机、方式及资源使用。我们提出MASkills，一种通过智能体技能持续优化多智能体LLM系统的框架。MASkills引入技能条件信用分配、层级信用聚合与动量平滑优化的新机制，支持技能库通过精炼、归纳、整合与剪枝不断演化。在HotpotQA、LoCoMo和GAIA上的实验表明，该方法在多种代理任务中均有效。代码已开源：https://github.com/DaRL-GenAI/MASkills
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。