Alternatives and similar repositories for trl

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

• brendanhogan / picoDeepResearch
  ☆68Updated 5 months ago
• alexzhang13 / rlm
  Super basic implementation (gist-like) of RLMs with REPL environments.
  ☆204Updated 2 weeks ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆109Updated 7 months ago
• janhq / verifiers-deepresearch
  Verifiers for LLM Reinforcement Learning
  ☆77Updated last month
• LLMSELECTOR / LLMSELECTOR
  ☆79Updated last month
• HishamAlyahya / semantic_backprop
  Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖
  ☆76Updated 10 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆79Updated 7 months ago
• PrimeIntellect-ai / genesys
  ☆135Updated 7 months ago
• HyperPotatoNeo / RSA
  ☆71Updated last month
• phunterlau / paper_without_code
  LLM reads a paper and produce a working prototype
  ☆57Updated 6 months ago
• facebookresearch / collaborative-reasoner
  Source code for the collaborative reasoner research project at Meta FAIR.
  ☆103Updated 6 months ago
• Xalp / ECHO
  Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)
  ☆91Updated 9 months ago
• SalesforceAIResearch / perfcodegen
  ☆43Updated 5 months ago
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆99Updated this week
• menloresearch / ReZero
  ☆158Updated 6 months ago
• SakanaAI / natural_niches
  The code repository of the paper: Competition and Attraction Improve Model Fusion
  ☆161Updated 2 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 this week
• axolotl-ai-cloud / grpo_code
  A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.
  ☆40Updated 6 months ago
• NVlabs / UniversalDeepResearch
  Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)
  ☆445Updated 2 months ago
• ALucek / GRPO-Training
  An overview of GRPO & DeepSeek-R1 Training with Open Source GRPO Model Fine Tuning
  ☆37Updated 5 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**.
  ☆57Updated 5 months ago
• pgasawa / BARE
  Leveraging Base Language Models for Few-Shot Synthetic Data Generation
  ☆36Updated last week
• AgnostiqHQ / multi-agent-llm
  Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)
  ☆120Updated 8 months ago
• mitkox / oda-r
  oda-r is a professional-grade compiler for Declarative Self-improving Python (DSPy), featuring comprehensive error handling, logging, and…
  ☆38Updated 9 months ago
• huggingface / smol2operator
  ☆112Updated last month
• StigLidu / DualDistill
  [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
  ☆101Updated 2 months ago
• Columbia-NLP-Lab / PAPILLON
  Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles
  ☆59Updated 5 months ago
• kurakurai / Luth
  Luth is a state-of-the-art series of fine-tuned LLMs for French
  ☆37Updated 2 weeks ago
• lamm-mit / PRefLexOR
  Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning
  ☆232Updated 8 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆172Updated 9 months ago