LARP: Language-Agent Role Play for Open-World Games

TL;DR

LARP introduces a cognitive architecture for language agents that enhances their adaptability, memory, and personality alignment in open-world games, improving long-term coherence and user interaction.

Contribution

The paper presents a novel framework integrating memory, decision-making, and personality alignment for language agents in open-world gaming environments.

Findings

Enhanced agent adaptability in complex environments

Improved long-term memory and coherence

Diverse personality simulation capabilities

Abstract

Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to complex environments and consistently maintain a long-term memory to ensure coherent actions. To bridge the gap between language agents and open-world games, we introduce Language Agent for Role-Playing (LARP), which includes a cognitive architecture that encompasses memory processing and a decision-making assistant, an environment interaction module with a feedback-driven learnable action space, and a postprocessing method that promotes the alignment of various personalities. The LARP framework refines interactions between users and agents, predefined with unique backgrounds and personalities, ultimately enhancing the gaming experience in open-world contexts. Furthermore, it highlights the diverse uses of language models in a range of areas such as entertainment, education, and various simulation scenarios. The project page is released at https://miao-ai-lab.github.io/LARP/.