Large Language Models (LLMs) demonstrate impressive general capabilities but often struggle with step-by-step procedural reasoning, a critical challenge in complex interactive environments. While retrieval-augmented methods like GraphRAG attempt to bridge this gap, their fragmented entity-relation graphs hinder the construction of coherent, multi-step plans. In this paper, we propose a novel framework based on Goal-Oriented Graphs (GoGs), where each node represents a goal and edges encode logical dependencies between them. This structure enables the explicit retrieval of causal reasoning paths by identifying a high-level goal and recursively retrieving its prerequisites, forming a coherent chain to guide the LLM. Through extensive experiments on the Minecraft testbed, a domain that demands robust multi-step planning and provides rich procedural knowledge, we demonstrate that GoG substantially improves procedural reasoning and significantly outperforms GraphRAG and other state-of-the-art baselines.
@article{arxiv.2505.18607,
title = {From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft},
author = {Jonathan Leung and Yongjie Wang and Zhiqi Shen},
journal= {arXiv preprint arXiv:2505.18607},
year = {2026}
}