AlphaUncommon
TsinghuaC3I/MARTI
[ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference
- Owner
- TsinghuaC3I (organization)
- Stars
- Stars: 572
- Forks
- Forks: 50
- Language
- Python
- License
- MIT
- Created
- 2025
- Topics
- deepseek-r1large-language-modelsmulti-agent-reinforcement-learningmulti-agent-systemsqwenverlopenrlhflarge-reasoning-modelsautogencamel
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by TsinghuaC3I
All 7 repos by TsinghuaC3I- TsinghuaC3I/Awesome-RL-for-LRMsStars: 2,498TeXRC
- TsinghuaC3I/Awesome-Memory-for-AgentsStars: 668Alpha
- TsinghuaC3I/Unify-Post-TrainingStars: 220PythonPrototype
- TsinghuaC3I/SSRLStars: 210PythonPrototype
- TsinghuaC3I/MedXpertQAStars: 185PythonPrototype
- TsinghuaC3I/Fourier-Position-EmbeddingStars: 122PythonPrototype
Nearby in Python
All Python repos- gradio-app/daggrStars: 572PythonAlpha
- oliver-kriska/claude-elixir-phoenixStars: 572PythonAlpha
- jxnl/personal-monorepo-templateStars: 572PythonAlpha
- logsol/Github-Auto-DeployStars: 572PythonAlpha
- mbj4668/pyangStars: 572PythonAlpha
- enzet/map-machineStars: 572PythonAlpha