metauto-ai / HGMLinks
𧬠The Huxley-Gâdel Machine
β305Updated 2 weeks ago
Alternatives and similar repositories for HGM
Users that are interested in HGM are comparing it to the libraries listed below
Sorting:
- SoTA Approach for ARC-AGI 2β151Updated 2 months ago
- A Tree Search Library with Flexible API for LLM Inference-Time Scalingβ494Updated 2 weeks ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generaβ¦β225Updated last week
- Super basic implementation (gist-like) of RLMs with REPL environments.β278Updated last month
- Train your own SOTA deductive reasoning modelβ107Updated 9 months ago
- The State Of The Art, intelligenceβ156Updated 3 months ago
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" π€β76Updated last year
- Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"β107Updated last week
- accompanying material for sleep-time compute paperβ118Updated 7 months ago
- This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.β366Updated this week
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.β352Updated 5 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusionβ167Updated 3 months ago
- Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoningβ235Updated 9 months ago
- β105Updated 5 months ago
- Source code for the collaborative reasoner research project at Meta FAIR.β111Updated 7 months ago
- Prompts used in the Automated Auditing Blog Postβ125Updated 4 months ago
- Public repository containing METR's DVC pipeline for eval data analysisβ143Updated 8 months ago
- ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolutionβ705Updated last week
- β59Updated 10 months ago
- Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)β450Updated 3 months ago
- β66Updated 4 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.β330Updated last year
- look how they massacred my boyβ63Updated last year
- Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"β351Updated 11 months ago
- β136Updated 8 months ago
- CodeScientist: An automated scientific discovery system for code-based experimentsβ303Updated last week
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.β388Updated this week
- β79Updated 2 months ago
- Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"β318Updated 3 weeks ago
- A framework for optimizing DSPy programs with RLβ293Updated 3 weeks ago