Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
For developers of LLM-based multi-agent systems, Meta-Team provides a method to automatically improve system performance from execution experience, addressing a key bottleneck in real-world deployment.
Meta-Team addresses the challenge of experience-driven evolution in LLM-based multi-agent systems by preserving execution context and coordinating post-task communication, enabling multi-scale self-evolution. It consistently outperforms baselines across six long-horizon benchmarks, demonstrating more reliable and scalable self-evolution.
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.