MAS-on-the-Fly: 在测试时动态适应基于大语言模型的多智能体系统
MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems
AI总结:
MASFly通过动态适应机制在测试时优化多智能体系统,利用检索增强和经验引导机制提升任务适应性和性能。
摘要:
基于大语言模型(LLM)的多智能体系统(MAS)已崭露头角,成为解决复杂任务的一种有前景的范式。然而,现有工作往往依赖于手动设计或“一刀切”自动化,缺乏部署后动态适应能力。受生物系统适应机制的启发,我们引入了MASFly,一种新的多智能体框架,能够在测试时实现动态适应。为适应系统生成,MASFly采用了一种检索增强的SOP实例化机制,利用自构建的成功协作模式库,使LLM能够为新查询生成定制化的MAS。对于适应性执行,MASFly整合了经验引导的监督机制,其中专门的Watcher智能体通过参考个性化经验池监控系统行为,并提供实时干预。广泛的实验表明,MASFly实现了最先进的性能,特别是在TravelPlanner基准测试中,成功率达到61.7%,同时表现出强大的任务适应性和鲁棒性。
英文摘要:
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.
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。