Highlights
- Pro
Stars
Research artifacts from Hyra (/ˈhaɪ.rɑː/)
Measuring and evolving with the frontier of agent work
A compact high-signal benchmark for evaluating frontier agents
A general framework for strategically scaling evaluation-driven discovery loops, discovering state-of-the-art solutions on 21 open-ended problems.
Cited 83-model x 49-benchmark LLM evaluation matrix with 18 matrix completion methods
AI agents running research on single-GPU nanochat training automatically
AI-Driven Scientific, Algorithmic, and Systems Discovery
PaperBanana: Automating Academic Illustration For AI Scientists
ThetaEvolve: Test-time Learning on Open Problems, enabling RL training on AlphaEvolve/OpenEvolve and emphasizing scaling test-time compute
A living benchmark framework for symbolic regression
Framework for evaluating and improving agents
A Neural Symbolic Model for Space Physics
A benchmark for LLMs on complicated tasks in the terminal
An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.
Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬
Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"
AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.
[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.
🙌 OpenHands: AI-Driven Development
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…