Alternatives and similar repositories for system-2-research

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

• open-thought / reasoning-gym
  procedural reasoning datasets
  ☆1,082Updated last week
• trotsky1997 / MathBlackBox
  ☆1,034Updated 8 months ago
• huggingface / search-and-learn
  Recipes to scale inference-time compute of open models
  ☆1,111Updated 3 months ago
• facebookresearch / coconut
  Training Large Language Model to Reason in a Continuous Latent Space
  ☆1,256Updated 3 weeks ago
• srush / awesome-o1
  A bibliography and survey of the papers surrounding o1
  ☆1,206Updated 9 months ago
• EleutherAI / cookbook
  Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
  ☆813Updated last month
• facebookresearch / MLGym
  MLGym A New Framework and Benchmark for Advancing AI Research Agents
  ☆553Updated 3 weeks ago
• NousResearch / atropos
  Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …
  ☆670Updated this week
• McGill-NLP / nano-aha-moment
  Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
  ☆521Updated last month
• NousResearch / Open-Reasoning-Tasks
  A comprehensive repository of reasoning tasks for LLMs (and beyond)
  ☆450Updated 11 months ago
• groundlight / r1_vlm
  Build your own visual reasoning model
  ☆407Updated last week
• ezelikman / quiet-star
  Code for Quiet-STaR
  ☆739Updated last year
• ekinakyurek / marc
  Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
  ☆328Updated 9 months ago
• seal-rg / recurrent-pretraining
  Pretraining and inference code for a large-scale depth-recurrent language model
  ☆825Updated this week
• openai / mle-bench
  MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
  ☆922Updated this week
• mlfoundations / evalchemy
  Automatic evals for LLMs
  ☆523Updated 2 months ago
• WecoAI / aideml
  AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
  ☆1,011Updated 3 weeks ago
• wasiahmad / Awesome-LLM-Synthetic-Data
  A reading list on LLM based Synthetic Data Generation 🔥
  ☆1,395Updated 3 months ago
• microsoft / Samba
  [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
  ☆908Updated 4 months ago
• PrimeIntellect-ai / prime-rl
  Decentralized RL Training at Scale
  ☆546Updated this week
• bespokelabsai / curator
  Synthetic data curation for post-training and structured data extraction
  ☆1,491Updated last month
• LambdaLabsML / distributed-training-guide
  Best practices & guides on how to write distributed pytorch training code
  ☆470Updated 6 months ago
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆247Updated last week
• carlini / yet-another-applied-llm-benchmark
  A benchmark to evaluate language models on questions I've previously asked them to solve.
  ☆1,029Updated 4 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆264Updated 2 weeks ago
• jerber / lang-jepa
  ☆119Updated 8 months ago
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆193Updated last year
• predibase / llm_distillation_playbook
  Best practices for distilling large language models.
  ☆574Updated last year
• SWE-Gym / SWE-Gym
  Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
  ☆531Updated last month
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆613Updated last week