AIApr 2, 2024

A Survey on Large Language Model-Based Game Agents

Georgia Tech
arXiv:2404.02039v4126 citationsh-index: 33Has Code
Originality Synthesis-oriented
AI Analysis

It provides a comprehensive overview for researchers and developers interested in using game environments as testbeds for AI capabilities, but it is incremental as it synthesizes existing work without new experimental results.

This survey reviews large language model-based game agents (LLMGAs) by proposing a unified reference architecture that synthesizes studies around memory, reasoning, and perception-action interfaces for single agents, and communication protocols for multi-agent coordination, linking game genres to agent requirements.

Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the emergence of Large Language Models (LLMs) provides new opportunities to endow these agents with generalizable reasoning, memory, and adaptability in complex game environments. This survey offers an up-to-date review of LLM-based game agents (LLMGAs) through a unified reference architecture. At the single-agent level, we synthesize existing studies around three core components: memory, reasoning, and perception-action interfaces, which jointly characterize how language enables agents to perceive, think, and act. At the multi-agent level, we outline how communication protocols and organizational models support coordination, role differentiation, and large-scale social behaviors. To contextualize these designs, we introduce a challenge-centered taxonomy linking six major game genres to their dominant agent requirements, from low-latency control in action games to open-ended goal formation in sandbox worlds. A curated list of related papers is available at https://github.com/git-disl/awesome-LLM-game-agent-papers

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes