Alternatives and similar repositories for system-2-research

Users that are interested in system-2-research are comparing it to the libraries listed below

• trotsky1997 / MathBlackBox
  ☆1,024Updated 5 months ago
• srush / awesome-o1
  A bibliography and survey of the papers surrounding o1
  ☆1,194Updated 6 months ago
• open-thought / reasoning-gym
  procedural reasoning datasets
  ☆625Updated this week
• huggingface / search-and-learn
  Recipes to scale inference-time compute of open models
  ☆1,087Updated last week
• willccbb / verifiers
  Verifiers for LLM Reinforcement Learning
  ☆1,057Updated this week
• microsoft / Samba
  [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  ☆876Updated last month
• facebookresearch / coconut
  Training Large Language Model to Reason in a Continuous Latent Space
  ☆1,135Updated 4 months ago
• McGill-NLP / nano-aha-moment
  Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
  ☆464Updated last week
• ezelikman / quiet-star
  Code for Quiet-STaR
  ☆732Updated 9 months ago
• EleutherAI / cookbook
  Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
  ☆793Updated last month
• WecoAI / aideml
  AIDE: AI-Driven Exploration in the Space of Code. State of the Art machine Learning engineering agents that automates AI R&D.
  ☆912Updated last month
• huggingface / lighteval
  Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
  ☆1,574Updated last week
• maitrix-org / llm-reasoners
  A library for advanced large language model reasoning
  ☆2,132Updated last month
• ekinakyurek / marc
  Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
  ☆309Updated 6 months ago
• facebookresearch / MLGym
  MLGym A New Framework and Benchmark for Advancing AI Research Agents
  ☆499Updated 3 weeks ago
• SWE-Gym / SWE-Gym
  Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
  ☆477Updated 3 weeks ago
• NousResearch / Open-Reasoning-Tasks
  A comprehensive repository of reasoning tasks for LLMs (and beyond)
  ☆443Updated 8 months ago
• ContextualAI / HALOs
  A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
  ☆851Updated this week
• seal-rg / recurrent-pretraining
  Pretraining code for a large-scale depth-recurrent language model
  ☆770Updated this week
• stanfordnlp / pyreft
  Stanford NLP Python library for Representation Finetuning (ReFT)
  ☆1,482Updated 3 months ago
• SimpleBerry / LLaMA-O1
  Large Reasoning Models
  ☆804Updated 6 months ago
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆367Updated last week
• huggingface / cosmopedia
  ☆517Updated 6 months ago
• openai / mle-bench
  MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
  ☆728Updated 2 weeks ago
• xfactlab / orpo
  Official repository for ORPO
  ☆453Updated last year
• argilla-io / distilabel
  Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…
  ☆2,724Updated this week
• wasiahmad / Awesome-LLM-Synthetic-Data
  A reading list on LLM based Synthetic Data Generation 🔥
  ☆1,287Updated 2 weeks ago
• NousResearch / atropos
  Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …
  ☆447Updated this week
• huggingface / nanotron
  Minimalistic large language model 3D-parallelism training
  ☆1,898Updated this week
• facebookresearch / swe-rl
  Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"
  ☆530Updated 2 months ago