Alternatives and similar repositories for GRPO

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

• waterhorse1 / Natural-language-RL
  Natural Language Reinforcement Learning
  ☆89Updated 6 months ago
• vwxyzjn / summarize_from_feedback_details
  ☆144Updated 7 months ago
• thu-coai / SPaR
  ☆47Updated 3 weeks ago
• McGill-NLP / agent-reward-bench
  AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
  ☆18Updated last month
• jackfsuia / nanoRLHF
  RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.
  ☆64Updated 4 months ago
• Asap7772 / understanding-rlhf
  Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…
  ☆29Updated last year
• jwhj / OREO
  ☆114Updated 5 months ago
• WooooDyy / LLM-Reverse-Curriculum-RL
  Implementation of the ICML 2024 paper "Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning" pr…
  ☆106Updated last year
• Gabesarch / ICAL
  ☆44Updated last month
• ltzheng / SimpleTIR
  End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  ☆71Updated this week
• Yu-Fangxu / FoR
  [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  ☆99Updated 3 weeks ago
• YangLing0818 / SuperCorrect-llm
  [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
  ☆74Updated 3 months ago
• WindyLee0822 / Process_Q_Model
  official implementation of paper "Process Reward Model with Q-value Rankings"
  ☆60Updated 4 months ago
• mnoukhov / async_rlhf
  Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models
  ☆58Updated 2 months ago
• holarissun / RewardModelingBeyondBradleyTerry
  official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…
  ☆62Updated 3 months ago
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆107Updated last month
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆107Updated 5 months ago
• efficientscaling / Z1
  Repo for "Z1: Efficient Test-time Scaling with Code"
  ☆63Updated 2 months ago
• AlphaPav / mem-kk-logic
  On Memorization of Large Language Models in Logical Reasoning
  ☆67Updated 3 months ago
• CMU-AIRe / MRT
  Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".
  ☆95Updated 3 months ago
• GuanghaoYe / Emergence-of-Thinking
  ☆52Updated 4 months ago
• liziniu / ReMax
  Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)
  ☆186Updated last year
• architsharma97 / dpo-rlaif
  ☆98Updated last year
• amazon-science / PAE
  ☆61Updated 3 months ago
• jwliao-ai / MARFT
  MARFT stands for Multi-Agent Reinforcement Fine-Tuning. This repository implements an LLM-based multi-agent reinforcement fine-tuning fra…
  ☆44Updated 2 weeks ago
• dongxiangjue / Awesome-LLM-Self-Improvement
  A curated list of awesome LLM Inference-Time Self-Improvement (ITSI, pronounced "itsy") papers from our recent survey: A Survey on Large …
  ☆81Updated 6 months ago
• swtheing / PF-PPO-RLHF
  ☆33Updated 9 months ago
• cmu-l3 / neurips2024-inference-tutorial-code
  NeurIPS 2024 tutorial on LLM Inference
  ☆45Updated 6 months ago
• yihedeng9 / rlhf-summary-notes
  A brief and partial summary of RLHF algorithms.
  ☆129Updated 4 months ago
• kyegomez / Lets-Verify-Step-by-Step
  "Improving Mathematical Reasoning with Process Supervision" by OPENAI
  ☆109Updated last week