Pinned Loading

1. strands-sglang strands-sglang Public

   SGLang model provider for Strands Agents for on-policy agentic RL training.

   Python 26 2

2. Think-RM Think-RM Public

   [NeurIPS 2025] Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models

   Python 16 1

3. strands-env strands-env Public

   Standardizing environment infrastructure with Strands Agents — step, observe, reward.

   Python 8 3

4. uncertainty-router uncertainty-router Public

   [NeurIPS 2025] Ask a Strong LLM Judge when Your Reward Model is Uncertain

   Python 6

5. OpenKimi OpenKimi Public

   Reproduce Kimi K1.5/K2 RL algorithm and rollout system

   Python 12 1