Skill-MAS: 演化元技能以自动生成多智能体系统
Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
AI总结：
提出Skill-MAS，通过将高层编排能力解耦为可演化的元技能，在无需参数更新的情况下实现经验保留，利用多轨迹采样和选择性反思优化元技能，在多个基准和LLM上取得显著性能提升且成本可控。
摘要：
基于大型语言模型（LLM）的自动多智能体系统（MAS）生成已成为处理复杂任务的关键前沿。然而，现有方法在模型能力和经验保留之间面临两难困境。推理时MAS利用冻结的尖端LLM，但重复相同搜索而不从过去经验中学习。相反，训练时MAS通过梯度更新内化经验，但受限于较小模型的低能力上限，且难以扩展到大型尖端LLM。为弥合这一差距，我们提出Skill-MAS，一种新颖的第三条路径，通过将高层编排能力概念化为可演化的元技能，将经验保留与参数更新解耦。Skill-MAS通过一个封闭优化循环来精炼这种架构知识：（1）多轨迹采样在当前元技能下为每个任务采样行为分布；（2）选择性反思自适应选择优先任务，并应用分层对比分析将系统经验蒸馏为可泛化的策略级原则。在四个复杂基准和四个不同LLM上的大量实验表明，Skill-MAS不仅实现了显著的性能提升，而且保持了良好的成本-性能权衡。进一步分析揭示，演化后的元技能高度鲁棒，并在未见任务和不同LLM之间表现出强迁移性。
英文摘要：
Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing methods face a dilemma between model capability and experience retention. Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience. Conversely, Training-time MAS internalizes experience via gradient updates but is constrained by the low capability ceiling of smaller models, and is hard to scale to large frontier LLMs. To bridge this gap, we propose Skill-MAS, a novel third path that decouples experience retention from parametric updates by conceptualizing the high-level orchestration capability as an evolvable Meta-Skill. Skill-MAS refines this architectural knowledge through a closed optimization loop: (1) Multi-Trajectory Rollout samples a behavioral distribution for each task under the current Meta-Skill; and (2) Selective Reflection adaptively selects priority tasks and applies hierarchical contrastive analysis to distill systemic experience into generalizable, strategy-level principles. Extensive experiments across four complex benchmarks and four distinct LLMs demonstrate that Skill-MAS not only achieves remarkable performance gains but also maintains a favorable cost-performance trade-off. Further analysis reveals that the evolved Meta-Skills are highly robust and exhibit strong transferability across unseen tasks and different LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
