MARTI
TsinghuaC3I द्वारा
[ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference
README से
MARTI: A Framework for LLM-based Multi-Agent Reinforced Training and Inference If you like our project, please give us a star ⭐ on GitHub for the latest update. MARTI is an open-source framework for training LLM-based Multi-Agent Systems (MAS) with Reinforcement Learning (RL). It enables powerful, scalable, and adaptive workflows by combining centralized multi-agent interactions with distributed policy training. MARTI supports both built-in graph-based workflows and popular third-party multi-agent frameworks. MARTI-v2 extends the framework with tree search-augmented RL for complex reasoning…
GitHub पर प्रोजेक्ट के README का अंश।
स्किल्स
एक ओपन-सोर्स प्रोजेक्ट — कोड एक्सप्लोर करें और इसे GitHub से सेल्फ़-होस्ट करें।