allenai / ScienceWorld
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
☆255Updated 6 months ago
Alternatives and similar repositories for ScienceWorld:
Users that are interested in ScienceWorld are comparing it to the libraries listed below
- An extensible benchmark for evaluating large language models on planning☆350Updated 2 weeks ago
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆136Updated last year
- ☆90Updated 9 months ago
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆274Updated last year
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆227Updated 5 months ago
- AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback☆107Updated 3 weeks ago
- ☆142Updated 11 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆162Updated last week
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆307Updated 6 months ago
- Reasoning with Language Model is Planning with World Model☆164Updated last year
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning☆439Updated 3 months ago
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆91Updated last year
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆134Updated 5 months ago
- ☆205Updated last year
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆151Updated 5 months ago
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking☆265Updated 9 months ago
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆254Updated 8 months ago
- ☆218Updated last year
- [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898☆216Updated 11 months ago
- The source code of the paper "Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Pla…☆93Updated 8 months ago
- An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]☆308Updated 11 months ago
- [ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"☆255Updated 3 weeks ago
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆182Updated this week
- Official Repo of LangSuitE☆83Updated 8 months ago
- Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)☆135Updated 5 months ago
- DialOp: Decision-oriented dialogue environments for collaborative language agents☆106Updated 5 months ago
- Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)☆209Updated this week
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆382Updated last year
- [NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents☆333Updated 7 months ago
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆265Updated 11 months ago