Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs
This addresses the challenge of coherent reasoning in LLMs for gaming applications, representing an incremental improvement over existing retrieval-augmented methods.
The paper tackles the problem of LLMs struggling with step-by-step reasoning in complex applications like games by proposing a Goal-Oriented Graphs framework, which significantly enhances reasoning ability in game-playing tasks, outperforming GraphRAG and other baselines on the Minecraft testbed.
Large Language Models (LLMs) demonstrate impressive general capabilities but often struggle with step-by-step reasoning, especially in complex applications such as games. While retrieval-augmented methods like GraphRAG attempt to bridge this gap through cross-document extraction and indexing, their fragmented entity-relation graphs and overly dense local connectivity hinder the construction of coherent reasoning. In this paper, we propose a novel framework based on Goal-Oriented Graphs (GoGs), where each node represents a goal and its associated attributes, and edges encode logical dependencies between goals. This structure enables explicit retrieval of reasoning paths by first identifying high-level goals and recursively retrieving their subgoals, forming coherent reasoning chains to guide LLM prompting. Our method significantly enhances the reasoning ability of LLMs in game-playing tasks, as demonstrated by extensive experiments on the Minecraft testbed, outperforming GraphRAG and other baselines.