像团队一样进化：基于LLM的多智能体系统的协作自我进化
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
AI总结：
提出Meta-Team框架，通过协作自我进化机制，基于执行经验改进多智能体系统的行为、协调和团队组织，在长周期任务中显著优于单智能体、手工MAS及先前进化方法。
摘要：
基于LLM的多智能体系统（MAS）已成为处理复杂和长周期任务的有效范式。然而，在实际任务中，MAS在执行过程中经常出现各种故障，且这些故障在设计阶段难以消除。这激发了经验驱动的MAS进化，即系统根据自身执行经验进行改进。然而，这种进化具有挑战性，因为MAS经验漫长而复杂，交织着多个智能体的执行链和通信消息，使得难以识别需要改进的内容。为应对这一挑战，我们提出了Meta-Team，一种基于协作自我进化的经验驱动MAS进化框架。Meta-Team保留每个智能体的执行上下文并协调任务后通信，使智能体能够交换分布式证据以进行进化。基于此设计，Meta-Team进行多尺度自我进化，将执行经验转化为对智能体行为、智能体间协调以及团队级组织的可复用改进。在六个长周期智能体基准测试中，Meta-Team始终优于单智能体系统、手工MAS和先前的MAS进化方法；进一步分析表明，Meta-Team实现了更可靠和可扩展的MAS自我进化。
英文摘要：
LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures during execution and such failures are difficult to eliminate during design. This motivates experience-driven MAS evolution, where a system improves based on its own execution experience. Yet such evolution is challenging because MAS experience is prolonged and intricate, interleaving multiple agents' execution chains and communication messages, which makes it difficult to identify what should be improved. To address this challenge, we propose Meta-Team, an experience-driven MAS evolution framework based on collaborative self-evolution. Meta-Team preserves the execution context of each agent and coordinates post-task communication, enabling agents to exchange distributed evidence for evolution. Building on this design, Meta-Team conducts multi-scale self-evolution, transforming execution experience into reusable improvements to agent behaviors, inter-agent coordination, and team-level organization. Across six long-horizon agent benchmarks, Meta-Team consistently outperforms single-agent systems, hand-crafted MAS, and prior MAS evolution methods; further analyses demonstrate that Meta-Team enables more reliable and scalable MAS self-evolution.
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。
