XMUDeepLIT/TTCS

Simple framework for training and evaluating math reasoning agents using local models, GRPO and vLLM.

[ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Official Repository of LatentSeek

Official Repo for SwS: A Weakness-driven Problem Synthesis Framework in RL for LLM Reasoning

Code for Base Models Can Reason by Taking a Cue From Training Data

RL with Experience Replay

[ACL'26 Oral, SAC Highlight] Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models

[COLM 2025] LIMO: Less is More for Reasoning

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information