Pinned Loading

1. Accordion-Thinking Accordion-Thinking Public

   Training LLM to fold the rasoning process

   Python 2

2. DARS DARS Public

   The official implemention of "Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration"

   Python 24

3. ReSocratic ReSocratic Public

   OptiBench and ReSocratic Synthesis Method

   Python 30 1

4. Mirror-Critique Mirror-Critique Public

   The official implemention of "Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers"

   Python 8 1