Alternatives and similar repositories for grpo_code

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

• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆108Updated 8 months ago
• s-smits / grpo-optuna
  Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
  ☆58Updated 3 weeks ago
• minosvasilias / simple_grpo
  Simple GRPO scripts and configurations.
  ☆59Updated 9 months ago
• bespokelabsai / verifiers
  Verifiers for LLM Reinforcement Learning
  ☆79Updated 6 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆82Updated 7 months ago
• arcee-ai / DAM
  ☆55Updated last year
• StigLidu / DualDistill
  [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
  ☆101Updated 2 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆173Updated 9 months ago
• PrimeIntellect-ai / genesys
  ☆135Updated 7 months ago
• Xalp / ECHO
  Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)
  ☆91Updated 9 months ago
• goncalorafaria / qalign
  QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.
  ☆24Updated 2 weeks ago
• brendanhogan / picoDeepResearch
  ☆68Updated 5 months ago
• argilla-io / argilla-cookbook
  Simple examples using Argilla tools to build AI
  ☆56Updated 11 months ago
• letta-ai / sleep-time-compute
  accompanying material for sleep-time compute paper
  ☆117Updated 6 months ago
• THU-KEG / Agentic-Reward-Modeling
  [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆109Updated 5 months ago
• axolotl-ai-cloud / axolotl-cookbook
  ☆36Updated 3 months ago
• Danau5tin / calculator_agent_rl
  Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.
  ☆58Updated 6 months ago
• collinear-ai / spider
  craft post-training data recipes
  ☆53Updated this week
• sunnweiwei / PPP-Agent
  ☆42Updated this week
• SinatrasC / entropix
  Entropy Based Sampling and Parallel CoT Decoding
  ☆17Updated last year
• axeld5 / pali_reason
  Testing paligemma2 finetuning on reasoning dataset
  ☆18Updated 10 months ago
• phunterlau / paper_without_code
  LLM reads a paper and produce a working prototype
  ☆57Updated 7 months ago
• OpenPipe / open_deep_research_training
  Training setup for Langchain's Open Deep Research
  ☆70Updated 2 months ago
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆100Updated 2 weeks ago
• facebookresearch / collaborative-reasoner
  Source code for the collaborative reasoner research project at Meta FAIR.
  ☆105Updated 6 months ago
• sher222 / LeReT
  Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
  ☆51Updated last year
• Alex-Gurung / ReasoningNCP
  Official repo for Learning to Reason for Long-Form Story Generation
  ☆72Updated 6 months ago
• alexzhang13 / rlm
  Super basic implementation (gist-like) of RLMs with REPL environments.
  ☆242Updated 3 weeks ago
• Intelligent-Internet / ii-thought
  II-Thought-RL is our initial attempt at developing a large-scale, multi-domain Reinforcement Learning (RL) dataset
  ☆28Updated 7 months ago
• haizelabs / j1-micro
  j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
  ☆98Updated 3 months ago