HomeResearch LibraryVoyager: An Open-Ended Embodied Agent with Large Langua…
Chapter 2 · 2023

Voyager: An Open-Ended Embodied Agent with Large Language Models

Guanzhi Wang, Yuqi Xie, Yunfan Jiang

Abstract

Voyager is the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention.

Eigenvector Breakthrough — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

Voyager demonstrates something critical for Zone III: agents can accumulate skills over time without retraining. The skill library mechanism — where the agent writes, tests, and stores reusable code — is a direct analogue to enterprise process libraries. The lesson is that Zone III agents should not start from scratch on every workflow; they should build institutional memory.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Topics

lifelong learningskill acquisitionembodied agentsopen-ended exploration