GAIR-NLP / ASI-ArchLinks
AlphaGo Moment for Model Architecture Discovery.
☆1,024Updated 2 weeks ago
Alternatives and similar repositories for ASI-Arch
Users that are interested in ASI-Arch are comparing it to the libraries listed below
Sorting:
- Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents☆1,616Updated last week
- Self-Adapting Language Models☆758Updated 3 weeks ago
- OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's A…☆873Updated 2 months ago
- Official Repository of Absolute Zero Reasoner☆1,660Updated 3 weeks ago
- Continuous Thought Machines, because thought takes time and reasoning is a process.☆1,261Updated last month
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,136Updated 6 months ago
- A Tree Search Library with Flexible API for LLM Inference-Time Scaling☆444Updated 3 weeks ago
- open-source coding LLM for software engineering tasks☆920Updated last month
- codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆501Updated last week
- Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning☆228Updated 6 months ago
- Atom of Thoughts for Markov LLM Test-Time Scaling☆583Updated 2 months ago
- CodeScientist: An automated scientific discovery system for code-based experiments☆289Updated 2 months ago
- The #1 open-source SWE-bench Verified implementation☆794Updated 2 months ago
- 🚀 MassGen: An Open-source Multi-Agent Scaling System Inspired by Grok Heavy and Gemini Deep Think. Join the discord channel: https://dis…☆369Updated this week
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search☆1,508Updated 3 months ago
- Releases from OpenAI Preparedness☆840Updated last week
- II-Researcher: a new open-source framework designed to aid building search / research agents☆466Updated 2 weeks ago
- Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input☆839Updated 2 months ago
- Pretraining and inference code for a large-scale depth-recurrent language model☆816Updated last month
- MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.☆2,822Updated last month
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆586Updated last week
- OctoTools: An agentic framework with extensible tools for complex reasoning☆1,342Updated 3 weeks ago
- ☆464Updated 2 weeks ago
- Collection of scripts and notebooks for OpenAI's latest GPT OSS models☆387Updated last week
- Open-source implementation of AlphaEvolve☆3,657Updated this week
- ☆264Updated 4 months ago
- An agent benchmark with tasks in a simulated software company.☆528Updated 2 weeks ago
- Frontier Models playing the board game Diplomacy.☆560Updated this week
- Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture.☆736Updated last month
- ☆425Updated 3 months ago