GAIR-NLP / ASI-ArchLinks
AlphaGo Moment for Model Architecture Discovery.
☆1,122Updated this week
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☆1,755Updated 3 months ago
- OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's A…☆947Updated 6 months ago
- Self-Adapting Language Models☆1,575Updated 4 months ago
- A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!☆1,172Updated 10 months ago
- A Tree Search Library with Flexible API for LLM Inference-Time Scaling☆494Updated last week
- Continuous Thought Machines, because thought takes time and reasoning is a process.☆1,578Updated last month
- Official Repository of Absolute Zero Reasoner☆1,769Updated 3 months ago
- codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆687Updated last month
- ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution☆705Updated this week
- ☆709Updated last week
- ☆5,799Updated this week
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search☆1,838Updated last month
- Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input☆924Updated 6 months ago
- Post-training with Tinker☆2,313Updated this week
- Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.☆751Updated 2 months ago
- Pretraining and inference code for a large-scale depth-recurrent language model☆850Updated last month
- ☆1,351Updated 2 months ago
- Agent0 Series: Self-Evolving Agents from Zero Data☆767Updated this week
- Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.☆1,835Updated this week
- ☆273Updated 7 months ago
- CodeScientist: An automated scientific discovery system for code-based experiments☆303Updated last week
- Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs☆2,023Updated 2 months ago
- dLLM: Simple Diffusion Language Modeling☆1,069Updated this week
- Collection of scripts and notebooks for OpenAI's latest GPT OSS models☆479Updated 3 months ago
- ☆696Updated 2 months ago
- OctoTools: An agentic framework with extensible tools for complex reasoning☆1,393Updated last month
- OpenAI Frontier Evals☆951Updated this week
- [NeurIPS 2025] Atom of Thoughts for Markov LLM Test-Time Scaling☆597Updated 2 weeks ago
- MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.☆3,000Updated 5 months ago
- This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.☆366Updated this week