Pinned Loading

1. OpenKimi OpenKimi Public

   [ICML2026] Reproduce Kimi K1.5/K2 RL algorithm and rollout system

   Python 19 2

2. Think-RM Think-RM Public

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

   Python 17 1

3. uncertainty-router uncertainty-router Public

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

   Python 10

4. HeaPA HeaPA Public

   Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

   Python 6

5. AlphaQuanter AlphaQuanter Public

   [ACL2026] AlphaQuanter: An End-to-End Tool-Orchestrated Agentic Reinforcement Learning Framework for Stock Trading.

   Python 55 9

6. RESD RESD Public

   [arXiv 2026] Learning from Rare Success and Rich Feedback via Reflection-Enhanced Self-Distillation

   Python 18 1