MasterVito/SwS

RL with Experience Replay

Scalable RL solution for advanced reasoning of language models

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

Democratizing Reinforcement Learning for LLMs

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

Fully open reproduction of DeepSeek-R1

[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.