CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents

2026-09-16

AI Summary

为解决查询路由与代理微调分离的问题，提出CERA-MoA框架，通过迭代强化学习使动态路由器与持续学习的代理协同进化，提高了任务性能和效率。

Abstract

Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, limiting their ability to respond to evolving agent capabilities. This disconnect prevents routing strategies from adapting to evolving agent capabilities during post-training and prevents agents from achieving synergistic data-driven specialization. To resolve this, we introduce CERA-MoA (Co-Evolving Router with continually learning Agents for Mixture-of-Agents), an iterative reinforcement learning framework where the dynamic router and independent agent policies co-evolve. We design a predictive familiarity estimator that leverages mid-layer hidden states to evaluate semantic competence among agents, avoiding the overhead of full rollouts. Based on these familiarity scores, a cumulative-threshold adaptive routing mechanism dynamically activates a tailored minimal agent subset, achieving a trade-off between task performance and efficiency. By proactively allocating targeted training samples to agents based on their evolving competence, CERA-MoA promotes capability differentiation. Extensive experiments across various domains demonstrate that CERA-MoA outperforms state-of-the-art static-agent routing and fix-workflow fine-tuning baselines.

Problem

• Mixture-of-Agents
• query routing
• agent fine-tuning
• evolving agent capabilities
• synergistic data-driven specialization

Innovation

• Co-Evolving Routing
• Continual Learning
• Familiarity Estimator
• Adaptive Routing Mechanism
• Capability Differentiation