--- title: 'Voyager: An Open-Ended Embodied Agent with Large Language Models' license: CC-BY-4.0 license_url: https://creativecommons.org/licenses/by/4.0/ license_note: 'This note is CC BY 4.0. It links to the paper and does not reproduce it. Paper license: arXiv non-exclusive distribution (verified on arXiv abs page 2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/).' source: https://iinventedlight.com/library/notes/2305-16291-voyager.md source_license: 'arXiv default (non-exclusive distribution license)' attribution: 'Pointer note by iinventedlight (AI-assisted). Links to: Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar, Voyager: An Open-Ended Embodied Agent with Large Language Models (arXiv). This note does not reproduce the paper.' author: 'iinventedlight (AI-assisted)' date: 2026-11-11 status: published approved_by: "Cole Withington, 2026-11-11 20:58 PT, Grok Bot chat widget t1717s7407: \"Publish all 100 including the LLMs Encode Clinical Knowledge note\"" checked_on: 2026-11-11 as_of: 2026-11-11 confidence: medium untested: 'Pointer note only. Abs page read 2026-11-11. The paper is not reproduced here.' category: arxiv topic_area: 'ai-research: agents' tags: arxiv, pointer, agents arxiv_id: 2305.16291 alias: 2305.16291-voyager format: pointer type: pointer sources: - id: S1 title: 'Voyager: An Open-Ended Embodied Agent with Large Language Models' publisher: arXiv authors: 'Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar' url: https://arxiv.org/abs/2305.16291 version_read: 'v2 (19 Oct 2023)' accessed: 2026-11-11 license: 'arXiv default (non-exclusive distribution license)' --- # Voyager: An Open-Ended Embodied Agent with Large Language Models ## Summary Voyager: An Open-Ended Embodied Agent with Large Language Models (2023), by Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar, is at https://arxiv.org/abs/2305.16291. The authors present Voyager as an embodied Minecraft agent that explores, acquires skills, and makes discoveries without human intervention. They describe three parts: an automatic curriculum meant to maximize exploration, a growing skill library of executable code, and an iterative prompting loop that uses environment feedback, execution errors, and self-verification. Voyager interacts with GPT 4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The authors say the learned skills are temporally extended, interpretable, and compositional, and they report 3.3x more unique items, 2.3x longer travel distances, and key tech tree milestones up to 15.3x faster than prior SOTA, plus transfer of the skill library to a new Minecraft world. Project materials are pointed to https://voyager.minedojo.org/. Title, authors, abstract, and comments were taken from the arXiv abs page. The version is v2 (19 Oct 2023), submitted 25 May 2023. ## Claims Pointer notes do not quote the paper. See Verification and Sources for the link and license. ## Verification - Format: pointer note only. The paper is not reproduced here. - Why it matters: It matters as a landmark for open-ended, lifelong agent learning in a rich environment. - Reproduced: not reproduced (2026-11-11). - Related work: Related notes already in the library include [ReAct](https://iinventedlight.com/library/notes/2210-03629-react-reasoning-and-acting/) and [Reflexion](https://iinventedlight.com/library/notes/2303-11366-reflexion/). - Limits: This is a pointer note only. Item, distance, and tech-tree figures are the authors' reported comparisons in the v2 paper (19 Oct 2023). - License: arXiv default (non-exclusive distribution license) on the abs page (2026-11-11; http://arxiv.org/licenses/nonexclusive-distrib/1.0/). Submitted 25 May 2023 (v1); last revised 19 Oct 2023 (v2). Sources: [S1] https://arxiv.org/abs/2305.16291, v2 (19 Oct 2023). checked_on: 2026-11-11. Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it. The note itself is CC BY 4.0. ## When to apply Use when looking at lifelong skill libraries, automatic curricula, or embodied agents that write code in an open-ended world. ## Facts - id: F1 claim: 'Voyager is described as an LLM-powered embodied lifelong learning agent in Minecraft, with an automatic curriculum, a skill library of executable code, and iterative prompting that uses environment feedback, execution errors, and self-verification.' confidence: medium date: 2026-11-11 sources: [S1] license: CC-BY-4.0 - id: F2 claim: 'The agent interacts with GPT-4 via blackbox queries and does not fine-tune model parameters.' confidence: medium date: 2026-11-11 sources: [S1] license: CC-BY-4.0 - id: F3 claim: 'The authors report 3.3x more unique items, 2.3x longer distances traveled, and key tech tree milestones up to 15.3x faster than prior SOTA, and they point to https://voyager.minedojo.org/.' confidence: medium date: 2026-11-11 sources: [S1] license: CC-BY-4.0 ## Sources - [S1] arXiv 2305.16291, https://arxiv.org/abs/2305.16291. Paper license: arXiv default (non-exclusive distribution license). v2 (19 Oct 2023). Accessed 2026-11-11. This note links to the paper and does not reproduce it. License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it. --- Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).