Alternatives and similar repositories for ab-mcts-arc2

Users that are interested in ab-mcts-arc2 are comparing it to the libraries listed below

• SakanaAI / natural_niches
  The code repository of the paper: Competition and Attraction Improve Model Fusion
  ☆159Updated last month
• SakanaAI / ShinkaEvolve
  ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution
  ☆478Updated last week
• facebookresearch / collaborative-reasoner
  Source code for the collaborative reasoner research project at Meta FAIR.
  ☆103Updated 5 months ago
• facebookresearch / llm-speedrunner
  The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…
  ☆99Updated 2 months ago
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆94Updated last week
• SakanaAI / ALE-Bench
  The official repository of ALE-Bench
  ☆117Updated last week
• SakanaAI / RLT
  Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
  ☆343Updated 3 months ago
• letta-ai / sleep-time-compute
  accompanying material for sleep-time compute paper
  ☆115Updated 5 months ago
• facebookresearch / aira-dojo
  AIRA-dojo: a framework for developing and evaluating AI research agents
  ☆95Updated last week
• SakanaAI / treequest
  A Tree Search Library with Flexible API for LLM Inference-Time Scaling
  ☆475Updated 2 months ago
• phunterlau / paper_without_code
  LLM reads a paper and produce a working prototype
  ☆56Updated 5 months ago
• NVlabs / RLP
  RLP: Reinforcement as a Pretraining Objective
  ☆69Updated last week
• MaximeRobeyns / self_improving_coding_agent
  A coding agent framework, that works on its own codebase.
  ☆122Updated 5 months ago
• yale-nlp / SciArena
  Analysis code for Neurips 2025 paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"
  ☆52Updated 2 months ago
• Think-a-Tron / evolve
  open source alpha evolve
  ☆67Updated 4 months ago
• benpry / why-think-step-by-step
  Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"
  ☆61Updated 6 months ago
• flowersteam / SOAR
  Implementation of SOAR
  ☆43Updated 2 weeks ago
• arcprize / ARC-AGI-3-Agents
  ☆86Updated this week
• SalesforceAIResearch / promptomatix
  An Automatic Prompt Optimization Framework for Large Language Models
  ☆122Updated 2 months ago
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆107Updated 7 months ago
• gkamradt / SnakeBench
  ☆93Updated 3 months ago
• allenai / codescientist
  CodeScientist: An automated scientific discovery system for code-based experiments
  ☆294Updated 3 months ago
• lucidrains / mind-evolution
  Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind
  ☆57Updated 4 months ago
• Arize-ai / prompt-learning
  ☆70Updated this week
• 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
• StigLidu / DualDistill
  [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
  ☆100Updated last month
• foundation-model-stack / bamba
  Train, tune, and infer Bamba model
  ☆133Updated 4 months ago
• benchflow-ai / pokemon-gym
  ☆85Updated 3 months ago
• allenai / autods
  ☆84Updated last month
• CLAIRE-Labo / EvoTune
  Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
  ☆112Updated 2 months ago