ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks
University of Oxford · The Chinese University of Hong Kong and Shanghai Artificial Intelligence Laboratory · Shanghai Jiaotong University · The University of Sydney · University of Oxford and University of Sydney · Shanghai AI Laboratory
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。DOI 10.18653/v1/2025.emnlp-main.808 ↗
摘要
Multi-agent systems have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving. However, current MAS frameworks are limited by poor flexibility and scalability, with underdeveloped optimization strategies. To address these challenges, we propose ReSo, which integrates task graph generation with a reward-driven two-stage agent selection process. The core of ReSo is the proposed Collaborative Reward Model, which can provide fine-grained reward signals for MAS cooperation for optimization. We also introduce an automated data synthesis framework for generating MAS benchmarks, without human annotations. Experimentally, ReSo matches or outperforms existing methods. ReSo achieves \textbf{33.7\%} and \textbf{32.3\%} accuracy on Math-MAS and SciBench-MAS SciBench, while other methods completely fail. The code and data are available at [Reso](https://github.com/hengzzzhou/ReSo).