dllm-reasoning/d1

Fully open reproduction of DeepSeek-R1

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

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

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

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

Scalable RL solution for advanced reasoning of language models

Implement a reasoning LLM in PyTorch from scratch, step by step

dLLM: Simple Diffusion Language Modeling

AllenAI's post-training codebase