MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and Inference
Tsinghua University · University of Washington · Shanghai Jiaotong University · Kuaishou- 快手科技 · Tsinghua University, Tsinghua University · Beijing Institute of Technology · Alibaba Group · Harbin Institute of Technology · Huazhong University of Science and Technology · Shanghai Artificial Intelligence Laboratory · Shanghai Artificial Intelligence Laboratory Tsinghua University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
We present MARTI (Multi-Agent Reinforced Training and Inference), an open-source framework designed to facilitate scalable and efficient learning of multi-agent LLM systems. MARTI supports centralized multi-agent interactions and distributed policy training, with the added capability of multi-turn asynchronous rollouts to enhance training efficiency. The framework includes dynamic workflows for multi-agent interactions, which integrate both rule-based verifiable rewards and LLM-based generative rewards. We validate the effectiveness of MARTI through comprehensive experiments on diverse mathematical tasks, demonstrating that multi-agent LLM-based systems outperform single-agent systems within the same inference budget after convergence. Our contributions lay the foundation for exploring scalable collaborations within LLM-based multi-agent systems and advancing the capabilities of large reasoning models.