HomeResearch LibraryGhost in the Minecraft: Generally Capable Agents for Op…
system architectureChapter 2arXiv · 2023

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

Xizhou Zhu (Tsinghua), Yuntao Chen (Tsinghua)

Abstract

We present GITM, a novel LLM-based agent system that leverages text-based knowledge and memory to handle complex tasks in open-world environments.

Eigenvector Insight — 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)

GITM's approach to decomposing open-ended goals into structured sub-tasks is directly applicable to enterprise process automation. The knowledge-memory integration pattern addresses the grounding problem for Zone III agents.

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.

Key Contributions

  • →Text-based knowledge integration
  • →Goal decomposition for open-world tasks
  • →Memory-augmented planning

Topics

open-world agentsknowledge memorylong-horizon planningtask decomposition