让大模型多智能体系统实时自适应结构，无需重训练。
MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems
- 用检索增强生成协作模式，按需构建智能体架构。
- 执行中通过观察器监测失败历史，异常时动态重构系统。
- 在旅行规划任务上达61.7%成功率，适配复杂动态任务。
基于大语言模型的多智能体系统已成为处理复杂任务的有前景范式。然而，现有方法通常依赖人工设计或“一刀切”自动化，部署后缺乏适应性。本文研究上下文结构自适应，即通过结构化经验同时指导查询相关的系统生成与运行时重构，且无需更新大模型参数。我们提出MASFly，通过两种互补机制实现该自适应：第一，检索增强的SOP实例化机制，检索并适配成功协作模式以构建查询相关的多智能体系统；第二，基于经验增强的过程监督机制，利用专用观察者智能体监控执行过程，依据过往失败经验在异常行为时重构系统。实验表明，MASFly达到当前最优性能，在TravelPlanner任务上取得61.7%的成功率，具备强任务适应性与鲁棒性。
原文摘要 · Abstract (English)
Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation and lack adaptability after deployment. We study in-context structural adaptation, where structured experience conditions both query-dependent system generation and execution-time reconfiguration without updating LLM parameters. We introduce MASFly, which realizes this adaptation through two complementary mechanisms. First, a retrieval-augmented SOP instantiation mechanism retrieves and adapts successful collaboration patterns to construct a query-specific MAS. Second, an experience-enhanced process supervision mechanism uses a dedicated Watcher agent to monitor execution against prior failure experience and reconfigure the system upon abnormal behavior. Experiments demonstrate that MASFly achieves state-ofthe-art performance, including a 61.7% success rate on TravelPlanner, with strong task adaptability and robustness.
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。