CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
cs.AI, cs.LG
Submitted: 2026-09-16
Updated: 2026-09-16
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
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.
Sources
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- Measuring Mathematical Problem Solving With the MATH Dataset
- LoRA: Low-Rank Adaptation of Large Language Models
- MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- TACO: Topics in Algorithmic COde generation dataset
- Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
- MALT: Improving Reasoning with Multi-Agent LLM Training
- LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
- Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
- RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents
- Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models
- MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
- R2-Router: A New Paradigm for LLM Routing with Reasoning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection