allenai / discoveryworldLinks
A virtual environment for developing and evaluating automated scientific discovery agents.
☆156Updated 2 months ago
Alternatives and similar repositories for discoveryworld
Users that are interested in discoveryworld are comparing it to the libraries listed below
Sorting:
- Repository for the paper Stream of Search: Learning to Search in Language☆147Updated 4 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆169Updated this week
- A benchmark that challenges language models to code solutions for scientific problems☆123Updated this week
- Open source interpretability artefacts for R1.☆140Updated last month
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆88Updated last week
- [ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery☆88Updated last month
- Governance of the Commons Simulation (GovSim)☆48Updated 4 months ago
- Benchmarking Agentic LLM and VLM Reasoning On Games☆146Updated 3 weeks ago
- Discovering Data-driven Hypotheses in the Wild☆85Updated 6 months ago
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆136Updated 6 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆107Updated last year
- ☆204Updated 3 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 4 months ago
- Implementation of the Quiet-STAR paper (https://arxiv.org/pdf/2403.09629.pdf)☆54Updated 9 months ago
- Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory☆61Updated last week
- Code for ExploreTom☆83Updated 5 months ago
- ☆86Updated 2 weeks ago
- Official repo for Learning to Reason for Long-Form Story Generation☆60Updated last month
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆173Updated 2 months ago
- This repository contains ScholarQABench data and evaluation pipeline.☆72Updated last month
- ☆114Updated 3 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆185Updated 6 months ago
- Official implementation of the ACL 2024: Scientific Inspiration Machines Optimized for Novelty☆79Updated last year
- ☆86Updated 3 weeks ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆193Updated 6 months ago
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation☆42Updated last year
- Code for the paper: "Learning to Reason without External Rewards"☆237Updated this week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆311Updated 6 months ago
- ☆93Updated 11 months ago
- [ACL 2024] <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>. It has also received the best poster award …☆41Updated 7 months ago