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
  ☆101Updated 6 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…
  ☆115Updated last year
• jwliao-ai / MARFT
  ☆75Updated 2 months ago
• vwxyzjn / summarize_from_feedback_details
  ☆160Updated last year
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆112Updated last year
• imagination-research / lbt
  [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
  ☆59Updated last year
• holarissun / RewardModelingBeyondBradleyTerry
  official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…
  ☆70Updated 9 months ago
• Yu-Fangxu / FoR
  [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  ☆116Updated this week
• thu-coai / SPaR
  ☆46Updated 7 months ago
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆141Updated 8 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…
  ☆32Updated last year
• efficientscaling / Z1
  [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"
  ☆68Updated 9 months ago
• WindyLee0822 / Process_Q_Model
  official implementation of paper "Process Reward Model with Q-value Rankings"
  ☆65Updated 11 months ago
• sail-sg / Precision-RL
  Defeating the Training-Inference Mismatch via FP16
  ☆180Updated 2 months ago
• jwhj / OREO
  ☆117Updated last year
• GuanghaoYe / Emergence-of-Thinking
  ☆53Updated 11 months ago
• thomasgauthier / LLM-self-play
  Minimal implementation of the Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models paper (ArXiv 20232401.01335)
  ☆29Updated last year
• kyegomez / Lets-Verify-Step-by-Step
  "Improving Mathematical Reasoning with Process Supervision" by OPENAI
  ☆114Updated last week
• THU-KEG / Agentic-Reward-Modeling
  [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆124Updated 7 months ago
• cmu-l3 / neurips2024-inference-tutorial-code
  NeurIPS 2024 tutorial on LLM Inference
  ☆47Updated last year
• mukhal / ThinkPRM
  Process Reward Models That Think
  ☆77Updated 2 months ago
• mnoukhov / async_rlhf
  Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models
  ☆68Updated 9 months ago
• sanyalsunny111 / LLM-Inheritune
  [TMLR 2026] When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
  ☆121Updated 11 months ago
• test-time-training / ttt-lm-kernels
  Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States
  ☆81Updated last year
• Gen-Verse / CURE
  [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
  ☆150Updated 4 months ago
• thunlp / Optima
  Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"
  ☆69Updated last year
• Open-Source-O1 / o1_Reasoning_Patterns_Study
  ☆104Updated last year
• convergence-ai / lm2
  Official repo of paper LM2
  ☆46Updated 11 months ago
• CLAIRE-Labo / EvoTune
  Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
  ☆125Updated 2 months ago
• TianduoWang / DPO-ST
  [ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
  ☆53Updated last year