MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models

TL;DR

MIMIC-Py is an extensible Python framework that uses personality-driven LLM agents for automated game testing, promoting reusability and minimal engineering effort across different game environments.

Contribution

It introduces a modular, configurable architecture for personality-driven LLM game testing tools, enabling easy deployment and extensibility across multiple game platforms.

Findings

Supports multiple interaction mechanisms with game APIs or synthesized code.

Designs a modular architecture that decouples planning, execution, and memory.

Facilitates deployment to new game environments with minimal effort.

Abstract

Modern video games are complex, non-deterministic systems that are difficult to test automatically at scale. Although prior work shows that personality-driven Large Language Model (LLM) agents can improve behavioural diversity and test coverage, existing tools largely remain research prototypes and lack cross-game reusability. This tool paper presents MIMIC-Py, a Python-based automated game-testing tool that transforms personality-driven LLM agents into a reusable and extensible framework. MIMIC-Py exposes personality traits as configurable inputs and adopts a modular architecture that decouples planning, execution, and memory from game-specific logic. It supports multiple interaction mechanisms, enabling agents to interact with games via exposed APIs or synthesized code. We describe the design of MIMIC-Py and show how it enables deployment to new game environments with minimal engineering effort, bridging the gap between research prototypes and practical automated game testing. The source code and a demo video are available on our project webpage: https://mimic-persona.github.io/MIMIC-Py-Home-Page/.