Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"
☆209Aug 13, 2026Updated last month
Alternatives and similar repositories for autodiscovery-neurips
Users that are interested in autodiscovery-neurips are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Discovering Data-driven Hypotheses in the Wild☆161Jun 9, 2025Updated last year
- Staging area for a public release of Theorizer☆172May 2, 2026Updated 4 months ago
- ☆154Aug 3, 2026Updated last month
- ☆138Sep 3, 2026Updated 3 weeks ago
- UQ: Assessing Language Models on Unsolved Questions☆30Aug 26, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- frozen-in-time version of our Paper Finder agent for reproducing evaluation results☆245Mar 17, 2026Updated 6 months ago
- Analysis code for Neurips 2025 paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆57Aug 6, 2025Updated last year
- CodeScientist: An automated scientific discovery system for code-based experiments☆351Mar 25, 2026Updated 6 months ago
- A Benchmark for Extracting Experiments from Scientific Literature | ICML'26 AI4Science!☆17Jul 29, 2026Updated last month
- Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research☆710Sep 9, 2026Updated 2 weeks ago
- ☆15Nov 19, 2025Updated 10 months ago
- ☆39Updated this week
- ☆15Nov 6, 2020Updated 5 years ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆146May 6, 2026Updated 4 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery☆41Jul 20, 2026Updated 2 months ago
- Repository for "Nearest neighbor search on embeddings rapidly identifies distant protein relations"☆13Apr 2, 2023Updated 3 years ago
- ☆11Feb 2, 2024Updated 2 years ago
- State-of-the-art paired encoder and decoder models (17M-1B params)☆81Aug 6, 2025Updated last year
- Incorporating distribution of experts in order to better predict the future discovery of novel scientific connections☆35Mar 23, 2026Updated 6 months ago
- PreScience: A Benchmark for Forecasting Scientific Contributions☆35Updated this week
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆42Oct 31, 2025Updated 10 months ago
- AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each…☆117Jun 24, 2026Updated 3 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆290Aug 5, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)☆470Aug 26, 2025Updated last year
- PhD/MBA-level human-annotated rubrics dataset across Physics, Chemistry, Finance and Consulting☆34Oct 30, 2025Updated 10 months ago
- Online materials for Social Media Data Analysis at the University of Konstanz☆10Oct 13, 2025Updated 11 months ago
- ☆17Sep 1, 2026Updated 3 weeks ago
- A comprehensive demonstration of Agentic DevOps using DSPy and Model Context Protocol (MCP)☆16May 31, 2025Updated last year
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆368Jun 23, 2025Updated last year
- Official implementation of DiscoGen, for "Procedural Generation of Algorithm Discovery Tasks in Machine Learning"☆50Sep 16, 2026Updated last week
- ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engi…☆295Apr 8, 2026Updated 5 months ago
- ☆13Apr 16, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆34Oct 8, 2025Updated 11 months ago
- Forecastbench Datasets, updated nightly☆39Updated this week
- Small, simple agent task environments for training and evaluation☆20Nov 1, 2024Updated last year
- ☆106Jul 16, 2026Updated 2 months ago
- ☆79Nov 23, 2025Updated 10 months ago
- 💻 SETA: Scaling Environments for Terminal Agents - Environments☆147Feb 16, 2026Updated 7 months ago
- Awesome Open-ended AI☆471Sep 19, 2026Updated last week