allenai / discoveryworld
A virtual environment for developing and evaluating automated scientific discovery agents.
☆96Updated last month
Related projects ⓘ
Alternatives and complementary repositories for discoveryworld
- Repository for the paper Stream of Search: Learning to Search in Language☆93Updated 3 months ago
- A Gymnasium-based Environment of the Abstraction and Reasoning Corpus (ARC)☆57Updated 2 months ago
- ☆101Updated 3 months ago
- A benchmark that challenges language models to code solutions for scientific problems☆87Updated this week
- ☆73Updated 4 months ago
- [ACL 2024] <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>. It has also received the best poster award …☆36Updated 3 weeks ago
- Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL☆43Updated last month
- ☆74Updated 3 weeks ago
- CiteME is a benchmark designed to test the abilities of language models in finding papers that are cited in scientific texts.☆38Updated 2 weeks ago
- Discovering Data-driven Hypotheses in the Wild☆41Updated this week
- ☆22Updated 5 months ago
- Learning Universal Predictors☆69Updated 3 months ago
- ☆137Updated 6 months ago
- Evaluation of neuro-symbolic engines☆33Updated 3 months ago
- ☆15Updated last month
- Bootstrapping ARC☆65Updated this week
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆84Updated 2 months ago
- ☆122Updated 2 weeks ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆22Updated this week
- Materials for ConceptARC paper☆77Updated 2 weeks ago
- We develop benchmarks and analysis tools to evaluate the causal reasoning abilities of LLMs.☆98Updated 5 months ago
- ☆25Updated 2 months ago
- Hypothetical Minds is an autonomous LLM-based agent for diverse multi-agent settings, integrating a Theory of Mind module Theory of Mind …☆18Updated 4 months ago
- Governance of the Commons Simulation (GovSim)☆21Updated 4 months ago
- ☆107Updated this week
- This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.☆99Updated this week
- Intrinsic Motivation from Artificial Intelligence Feedback☆119Updated last year
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆45Updated 5 months ago
- Can Language Models Solve Olympiad Programming?☆101Updated 3 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆84Updated 8 months ago