Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Odyssey: Empowering Minecraft Agents with Open-World Skills
| Date | Stars |
|---|---|
| 2026-07-31 | 399 |
| 2026-08-01 | 399 |
| 2026-08-06 | 399 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img src="./Odyssey/images/logo.jpg" width="38%"> </div> <h1 align="center">Empowering Minecraft Agents with Open-World Skills</h1> <div align="center"> <a href="https://arxiv.org/abs/2407.15325"><img src="https://img.shields.io/badge/arXiv-2407.15325-b31b1b.svg"/></a> <a href="https://github.com/zju-vipa/Odyssey/blob/master/LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue"/></a> <a href="https://github.com/zju-vipa/Odyssey"><img src="https://img.shields.io/badge/Dataset-Released-orange"/></a> <a href="https://github.com/zju-vipa/Odyssey"><img src="https://img.shields.io/badge/Project-Odyssey-yellow"/></a> <a href="https://github.com/zju-vipa/Odyssey"><img src="https://visitor-badge.laobi.icu/badge?page_id=zju-vipa.Odyssey"/></a> <a href="https://github.com/zju-vipa/Odyssey"><img src="https://img.shields.io/github/stars/zju-vipa/Odyssey"/></a> </div> Official codebase for the paper "[Odyssey: Empowering Minecraft Agents with Open-World Skills](https://arxiv.org/abs/2407.15325)". This codebase is based on the [Voyager](https://github.com/MineDojo/Voyager) framework. <div align="center"> <img src="./Odyssey/images/framework-1.png" width="100%"> </div> ## Overview **Abstract:** Recent studies have delved into constructing generalist agents for open-world environments like Minecraft. Despite the encouraging results, existing efforts mainly focus on solving basic programmatic tasks, e.g., material collection and tool-crafting following the Minecraft tech-tree, treating the ObtainDiamond task as the ultimate goal. This limitation stems from the narrowly defined set of actions available to agents, requiring them to learn effective long-horizon strategies from scratch. Consequently, discovering diverse gameplay opportunities in the open world becomes challenging. In this work, we introduce Odyssey, a new framework that empowers Large Language Model (LLM)-based agents with open-world skills to explore the vast Minecraft world. Odyssey comprises three key parts: - **(1) An interactive agent with an open-world skill library that consists of 40 primitive skills and 183 compositional skills.** - **(2) A fine-tuned LLaMA-3 model trained on a large question-answering dataset with 390k+ instruction entries derived from the Minecraft Wiki.** - **(3) A new agent capability benchmark includes the long-term planning task, the dynamic-immediate planning task, and the autonomous exploration task.** Extensive experiments demonstrate that the proposed Odyssey framework can effectively evaluate different capabilities of LLM-based agents. All datasets, model weights, and code are publicly available to motivate future research on more advanced autonomous agent solutions. ## News - **`[Apr 29, 2025]`** 🔥 We are very happy that **ODYSSEY** has been accepted by IJCAI 2025. - **`[Mar 5, 2025]`** 🔥 We have uploaded our new paper titled ["Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems"](https://arxiv.org/abs/2503.03505) to arXiv. - **`[Feb 23, 2025]`** 🔥 We have open-sourced the [Multi-Agent Framework](https://github.com/zju-vipa/Odyssey/tree/master/Multi-Agent) to align with our latest paper. - **`[Oct 1, 2024]`** 🔥 We have additionally compared more baselines (with different open-sourced LLMs and agents) and designed more test scenarios (for the long-term planning task and the dynamic-immediate planning task) in the updated version of the [paper](https://arxiv.org/abs/2407.15325). - **`[Sep 1, 2024]`** 🔥 We have additionally open-sourced the [Web Crawler Program](https://github.com/zju-vipa/Odyssey/tree/master/MC-Crawler), which was used to collect data from Minecraft Wikis. Researchers can modify this program to crawl data relevant to their needs. - **`[Aug 14, 2024]`** 🔥 We have additionally open-sourced the [Comprehensive Skill Library](https://github.com/zju-vipa/Odyssey/tree/master/MC-Comprehensive-Skill-Library), aiming to provide an automated tool to collect all
Excerpt of 21,563 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:94131145bec77bd7, topic:large-language-models, topic:llm
matched fp:94131145bec77bd7, topic:fine-tuning
matched fp:94131145bec77bd7, topic:llm-agent