EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation· EvoRouter: 通过洞见引导的在线策略蒸馏实现成本效益的多代理路由
Serving web queries at scale with multi-agent systems requires jointly configuring large language models, collaboration modes, agent counts, interaction rounds, and skills. However, the resulting configuration space grows combinatorially, while sparse execution rewards provide limited fine-grained supervision for interdependent planning decisions. We propose EvoRouter, a self-evolving multi-agent routing framework driven by insight-guided on-policy distillation. A dedicated expert periodically synthesizes performance-cost feedback from configuration trajectories across tasks into reusable conditional routing insights about capability requirements, returns from resource scaling, and interactions among configuration choices. A privileged teacher combines these evolving insights with current
提出EvoRouter框架，利用在线策略蒸馏实现成本效益的多代理路由配置。
- 核心方法
- 通过洞见引导的在线策略蒸馏，周期性地从任务配置轨迹中合成性能-成本反馈，转化为可复用的条件路由洞见。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 大规模网络查询中多代理系统配置空间组合性增长，执行奖励稀疏，难以提供细化监督。
- 关键实验
- 未提供
- 主要贡献
- EvoRouter能够高效地配置多代理系统，减少成本，提高性能。
- 意义与局限
- 为大规模多代理系统提供了新的配置方法，但可能受限于特定应用场景。