Pinned Loading

1. DARS DARS Public

   The official implemention of "Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration" (ICML 2026)

   Python 24

2. Prune-OPD Prune-OPD Public

   The official implemention of "Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning"

   Python 1

3. Accordion-Thinking Accordion-Thinking Public

   Training LLM to fold the rasoning process

   Python 4

4. ReSocratic ReSocratic Public

   OptiBench and ReSocratic Synthesis Method

   Python 35 2