SakanaAI / AI-Scientist-v2Links
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
☆1,921Updated last week
Alternatives and similar repositories for AI-Scientist-v2
Users that are interested in AI-Scientist-v2 are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] Automated Design of Agentic Systems☆1,477Updated 11 months ago
- Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents☆1,774Updated 4 months ago
- ☆277Updated 8 months ago
- AlphaGo Moment for Model Architecture Discovery.☆1,125Updated 3 weeks ago
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,180Updated 11 months ago
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆1,251Updated last week
- About Awesome things towards foundation agents. Papers / Repos / Blogs / ...☆1,915Updated 5 months ago
- [NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat☆3,844Updated 2 months ago
- This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.☆737Updated 4 months ago
- OctoTools: An agentic framework with extensible tools for complex reasoning☆1,404Updated 2 months ago
- AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.☆1,099Updated last month
- ☆2,507Updated this week
- Official Repository of Absolute Zero Reasoner☆1,779Updated 4 months ago
- ☆1,374Updated 3 months ago
- Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs☆2,120Updated 2 months ago
- OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's A…☆957Updated 7 months ago
- Repository for Zochi's Research☆297Updated last month
- Large Concept Models: Language modeling in a sentence representation space☆2,313Updated 11 months ago
- Continuous Thought Machines, because thought takes time and reasoning is a process.☆1,670Updated last week
- ☆574Updated 7 months ago
- A compilation of the best multi-agent papers☆1,130Updated this week
- [NeurIPS 2025] Atom of Thoughts for Markov LLM Test-Time Scaling☆624Updated last month
- Open-source implementation of AlphaEvolve☆4,981Updated last week
- Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning☆3,928Updated 3 weeks ago
- CodeScientist: An automated scientific discovery system for code-based experiments☆305Updated last month
- TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.☆3,212Updated 5 months ago
- An agent benchmark with tasks in a simulated software company.☆611Updated last month
- MLGym A New Framework and Benchmark for Advancing AI Research Agents☆583Updated 4 months ago
- [Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems☆1,527Updated 2 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,465Updated 3 weeks ago