An Appraisal-Based Chain-Of-Emotion Architecture for Affective Language Model Game Agents

TL;DR

This paper introduces a new chain-of-emotion architecture for affective game agents based on psychological appraisal, demonstrating improved emotional simulation and user experience over standard LLMs in empirical tests.

Contribution

It proposes a novel architecture for emotion simulation in game agents using LLMs and psychological appraisal, advancing affective agent development.

Findings

Outperforms standard LLM architectures on user experience metrics

Effective simulation of human-like emotions in game agents

Provides evidence for cognitive process-based affective agent design

Abstract

The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to developing agents that effectively simulate human emotions. Large language models (LLMs) might address these issues by tapping common patterns in situational appraisal. In three empirical experiments, this study tests the capabilities of LLMs to solve emotional intelligence tasks and to simulate emotions. It presents and evaluates a new chain-of-emotion architecture for emotion simulation within video games, based on psychological appraisal research. Results show that it outperforms standard LLM architectures on a range of user experience and content analysis metrics. This study therefore provides early evidence of how to construct and test affective agents based on cognitive processes represented in language models.