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

2026-04-08

AI Summary

This work addresses the challenge of efficiently automating testing in modern video games, which are inherently complex and non-deterministic, and where existing large language model (LLM)-based personality-driven testing approaches suffer from limited cross-game reusability. The authors propose a modular and extensible Python-based automated testing framework that, for the first time, treats configurable personality traits as a universal input. By decoupling the LLM agent’s planning, execution, and memory components, and supporting multi-game interaction through API or code synthesis, the framework substantially reduces the engineering effort required to adapt to new games. This design enables rapid cross-game deployment with minimal customization, simultaneously enhancing behavioral diversity and test coverage, thereby advancing personality-driven testing from a research prototype toward a practical, deployable tool.

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/.

Problem

• automated game testing
• personality-driven agents
• Large Language Models
• cross-game reusability
• non-deterministic systems

Innovation

• personality-driven agents
• Large Language Models
• modular architecture
• automated game testing
• behavioral diversity