2023ReviewedOpen access
Voyager: An Open-Ended Embodied Agent with Large Language Models
Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, Anima Anandkumar
NeurIPS 2023
Abstract
Demonstrates a continuously learning LLM agent in Minecraft that writes and executes code, highlighting autonomous operation and containment challenges.
Categories
#embodied-agent#autonomous-learning#code-execution
Framework mappings
OWASP Top 10 for Agentic Applications
- ASI10Rogue Agents
Cite
@inproceedings{wang2023voyager,
title = {{Voyager: An Open-Ended Embodied Agent with Large Language Models}},
author = {Guanzhi Wang and Yuqi Xie and Yunfan Jiang and Ajay Mandlekar and Chaowei Xiao and Yuke Zhu and Linxi Fan and Anima Anandkumar},
year = {2023},
booktitle = {NeurIPS 2023},
eprint = {2305.16291},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2305.16291}
}