A Survey on Large Language Model-Based Game Agents

2024-04-02

arXiv.org

AI Summary

This paper addresses the challenge of enabling human-like decision-making in game agents operating within complex environments. Methodologically, it proposes the first three-dimensional functional architecture—Memory–Reasoning–I/O—for LLM-driven game agents, systematically reviewing over 50 representative works across six game genres, including adventure, communication, and competitive games. The approach integrates multimodal perception, long-term memory, chain-of-thought reasoning, and game API integration to establish cross-genre unified evaluation dimensions. Key contributions include: (1) the first formalization of a functional architecture for LLM-based game agents; (2) the creation of an open-source, structured, and authoritative repository of relevant literature; and (3) an empirical analysis revealing critical performance bottlenecks and generalization limitations, thereby providing both a theoretical framework and a practical roadmap for AGI-oriented game agent research.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

The development of game agents holds a critical role in advancing towards Artificial General Intelligence. The progress of Large Language Models (LLMs) offers an unprecedented opportunity to evolve and empower game agents with human-like decision-making capabilities in complex computer game environments. This paper provides a comprehensive overview of LLM-based game agents from a holistic viewpoint. First, we introduce the conceptual architecture of LLM-based game agents, centered around three core functional components: memory, reasoning and in/output. Second, we survey existing representative LLM-based game agents documented in the literature with respect to methodologies and adaptation agility across six genres of games, including adventure, communication, competition, cooperation, simulation, and crafting&exploration games. Finally, we present an outlook of future research and development directions in this burgeoning field. A curated list of relevant papers is maintained and made accessible at: https://github.com/git-disl/awesome-LLM-game-agent-papers.

Problem

• Developing game agents with human-like decision-making using LLMs
• Surveying LLM-based agent methods across six game genres
• Outlining future research directions for LLM game agents

Innovation

• LLM-based game agents with memory, reasoning, input/output
• Survey of LLM agents across six game genres
• Future research directions for LLM game agents