allenai / discoveryworld
A virtual environment for developing and evaluating automated scientific discovery agents.
☆127Updated 3 weeks ago
Alternatives and similar repositories for discoveryworld:
Users that are interested in discoveryworld are comparing it to the libraries listed below
- Repository for the paper Stream of Search: Learning to Search in Language☆137Updated 2 weeks ago
- Benchmarking Agentic LLM and VLM Reasoning On Games☆114Updated this week
- Discovering Data-driven Hypotheses in the Wild☆55Updated 3 months ago
- ☆78Updated 7 months ago
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆242Updated 4 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆161Updated last week
- A benchmark that challenges language models to code solutions for scientific problems☆108Updated this week
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆125Updated 2 months ago
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation☆39Updated last year
- Can Language Models Solve Olympiad Programming?☆110Updated last month
- ☆128Updated 3 months ago
- ☆23Updated last year
- [ACL 2024] <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>. It has also received the best poster award …☆38Updated 3 months ago
- Replicating O1 inference-time scaling laws☆82Updated 2 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆81Updated 4 months ago
- Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL☆48Updated 4 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆98Updated 10 months ago
- [ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery☆53Updated 3 weeks ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆53Updated 2 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆182Updated 2 months ago
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆145Updated 2 months ago
- Code/data for MARG (multi-agent review generation)☆38Updated 3 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆71Updated last year
- ☆121Updated last week
- Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples☆73Updated last month
- Implementation of the Quiet-STAR paper (https://arxiv.org/pdf/2403.09629.pdf)☆51Updated 6 months ago
- We develop benchmarks and analysis tools to evaluate the causal reasoning abilities of LLMs.☆108Updated 8 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆120Updated 3 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆65Updated 6 months ago