Alternatives and similar repositories for MRT

Users that are interested in MRT are comparing it to the libraries listed below

• PRIME-RL / ImplicitPRM
  Repo of paper "Free Process Rewards without Process Labels"
  ☆165Updated 8 months ago
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆258Updated 6 months ago
• kanishkg / cognitive-behaviors
  ☆215Updated 7 months ago
• ltzheng / SimpleTIR
  End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  ☆318Updated last month
• GAIR-NLP / LIMR
  ☆212Updated 8 months ago
• GAIR-NLP / ToRL
  ☆309Updated 5 months ago
• hkust-nlp / dart-math
  [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
  ☆116Updated 11 months ago
• sail-sg / CPO
  [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.
  ☆131Updated 7 months ago
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆115Updated 6 months ago
• eddycmu / demystify-long-cot
  ☆326Updated 5 months ago
• QwenLM / ProcessBench
  Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"
  ☆176Updated 5 months ago
• RyanLiu112 / GenPRM
  [AAAI 2026] Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".
  ☆85Updated last week
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆180Updated 3 months ago
• ruixin31 / Spurious_Rewards
  ☆336Updated 3 months ago
• WooooDyy / MathCritique
  Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".
  ☆56Updated 11 months ago
• jwhj / OREO
  ☆116Updated 9 months ago
• IAAR-Shanghai / xVerify
  xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
  ☆138Updated 6 months ago
• thu-wyz / inference_scaling
  ☆76Updated 11 months ago
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆112Updated 9 months ago
• NineAbyss / S2R
  This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"
  ☆71Updated 6 months ago
• YangLing0818 / SuperCorrect-llm
  [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
  ☆83Updated 7 months ago
• Zanette-Labs / efficient-reasoning
  ☆67Updated 7 months ago
• CJReinforce / PURE
  Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"
  ☆139Updated 3 weeks ago
• TIGER-AI-Lab / General-Reasoner
  General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]
  ☆198Updated 2 weeks ago
• bethgelab / sober-reasoning
  A Sober Look at Language Model Reasoning
  ☆87Updated last month
• LLM360 / Reasoning360
  A repo for open research on building large reasoning models
  ☆112Updated last week
• YuxiXie / MCTS-DPO
  This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.
  ☆327Updated last year
• ElliottYan / LUFFY
  Official Repository of "Learning to Reason under Off-Policy Guidance"
  ☆364Updated last month
• WindyLee0822 / Process_Q_Model
  official implementation of paper "Process Reward Model with Q-value Rankings"
  ☆64Updated 9 months ago
• facebookresearch / sweet_rl
  Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
  ☆249Updated 6 months ago