{"type":"ScholarlyArticle","title":"Odyssey : Empowering Minecraft Agents with Open-World Skills","authors":[{"name":"Shunyu Liu","slug":"shunyu-liu","given":"Shunyu","family":"Liu","affiliation":""},{"name":"Yaoru Li","slug":"yaoru-li","given":"Yaoru","family":"Li","affiliation":""},{"name":"Kongcheng Zhang","slug":"kongcheng-zhang","given":"Kongcheng","family":"Zhang","affiliation":""},{"name":"Zhenyu Cui","slug":"zhenyu-cui","given":"Zhenyu","family":"Cui","affiliation":""},{"name":"Wenkai Fang","slug":"wenkai-fang","given":"Wenkai","family":"Fang","affiliation":""},{"name":"Yuxuan Zheng","slug":"yuxuan-zheng","given":"Yuxuan","family":"Zheng","affiliation":""},{"name":"Tongya Zheng","slug":"tongya-zheng","given":"Tongya","family":"Zheng","affiliation":""},{"name":"Mingli Song","slug":"mingli-song","given":"Mingli","family":"Song","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/22","url":"https://ijcai.org/proceedings/2025/22","pdf":"https://ijcai.org/proceedings/2025/0022.pdf","markdown":"https://ijcai.org/proceedings/2025/22.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/22","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Agent-based and Multi-agent Systems","track":"Main Track","number":22,"pages":{"first":187,"last":195},"keywords":["Natural Language Processing: NLP: Applications","Agent-based and Multi-agent Systems: MAS: Applications","Agent-based and Multi-agent Systems: MAS: Agent-based simulation and emergence"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}