Pinned Loading

1. OpenClaw-RL OpenClaw-RL Public

   OpenClaw-RL: Train any agent simply by talking

   Python 5.5k 597

2. MMaDA MMaDA Public

   MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

   Python 1.7k 89

3. LatentMAS LatentMAS Public

   [ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems

   Python 994 159

4. Open-AgentRL Open-AgentRL Public

   RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

   Python 555 56

5. ReasonFlux ReasonFlux Public

   [NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

   Python 538 37

6. dLLM-RL dLLM-RL Public

   [ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

   Python 510 43