Kwai-Klear/RLEP

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

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

[ICLR 2026] Official repository for the paper "LaSeR: Reinforcement Learning with Last-Token Self-Rewarding"

Fully open reproduction of DeepSeek-R1

A very simple GRPO implement for reproducing r1-like LLM thinking.

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

An extension of veRL for post-training LLM reasoners with on-policy self-distillation and self-distilled RLVR + the official codebase for RLRT (Rebellious Student)

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