allenai / ScienceWorldLinks
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
☆329Updated last month
Alternatives and similar repositories for ScienceWorld
Users that are interested in ScienceWorld are comparing it to the libraries listed below
Sorting:
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆144Updated last year
- An extensible benchmark for evaluating large language models on planning☆440Updated 3 months ago
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆289Updated 2 years ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆243Updated last month
- Reasoning with Language Model is Planning with World Model☆185Updated 2 years ago
- ☆109Updated last year
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning☆617Updated 5 months ago
- AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback☆125Updated 9 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆201Updated 9 months ago
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆323Updated last year
- This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'☆136Updated 7 months ago
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆275Updated 2 months ago
- [NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents☆454Updated last year
- An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]☆384Updated last year
- Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)☆159Updated last year
- ☆220Updated 2 years ago
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆284Updated last year
- ☆144Updated last year
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆147Updated last year
- Benchmarking Agentic LLM and VLM Reasoning On Games☆224Updated last month
- Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)☆272Updated last week
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆184Updated 7 months ago
- [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898☆233Updated last year
- DialOp: Decision-oriented dialogue environments for collaborative language agents☆111Updated last year
- ☆98Updated last year
- Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)☆218Updated 2 years ago
- ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate☆503Updated 8 months ago
- [NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling bett…☆294Updated last year
- Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Ziha…☆132Updated last year
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking☆267Updated last year