Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
About
Large Language Models (LLMs) have shown remarkable performance in completing various tasks. However, solving complex problems often requires the coordination of multiple agents, raising a fundamental question: how to effectively select and interconnect these agents. In this paper, we propose \textbf{Agent Q-Mix}, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. Our method learns decentralized communication decisions using QMIX value factorization, where each agent selects from a set of communication actions that jointly induce a round-wise communication graph. At its core, Agent Q-Mix combines a topology-aware GNN encoder, GRU memory, and per-agent Q-heads under a Centralized Training with Decentralized Execution (CTDE) paradigm. The framework optimizes a reward function that balances task accuracy with token cost. Across seven core benchmarks in coding, reasoning, and mathematics, Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure. Notably, on the challenging Humanity's Last Exam (HLE) using Gemini-3.1-Flash-Lite as a backbone, Agent Q-Mix achieves 20.8\% accuracy, outperforming Microsoft Agent Framework (19.2\%) and LangGraph (19.2\%), followed by AutoGen and Lobster by OpenClaw. These results underscore the effectiveness of learned, decentralized topology optimization in pushing the boundaries of multi-agent reasoning.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Code Generation | HumanEval | Accuracy97.56 | 99 | |
| Reasoning | MMLU-Pro | Accuracy92.86 | 95 | |
| Mathematics | AIME25 | Accuracy63.33 | 63 | |
| Code Generation | LiveCodeBench v6 | Accuracy100 | 58 | |
| Mathematics | HMMT | Accuracy53.33 | 26 | |
| Mathematics | Beyond | Accuracy42 | 26 | |
| Mathematics | AIME 26 | Accuracy60 | 26 | |
| Multi-task Language Understanding | MMLU-Pro | Performance92.86 | 10 | |
| Code Generation | LiveCode Bench | Total Tokens312 | 10 | |
| Mathematical Reasoning | Beyond AIME | Total Tokens708 | 10 |