Latest Advances on System-2 Reasoning

🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]

Explore the Multimodal “Aha Moment” on 2B Model

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Collect every awesome work about r1!

Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".

Qwen3 Fine-tuning: Medical R1 Style Chat

Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

Doge Family of Small Language Models

[ACL 2025] The code repository for "Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning" in PyTorch.

Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"

Code for "UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning"

A repo for open research on building large reasoning models

Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".

Simple repository for training small reasoning models

超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1

Auto-generate fallback and meter display from existing group info in d&b audiotechnik's R1 and ArrayCalc software.

A framework making it effortless to convert any llm model into a reasoning agent like o1 or DeepSeek's r1

Recreating the minimal training methods of DeepSeek-R1 for small langauge models.

Distributed Reinforcement Learning for LLM Fine-Tuning with multi-GPU utilization