MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Model

• URL: http://arxiv.org/abs/2510.01635v1
• Date: Thu, 02 Oct 2025 03:30:00 GMT
• Title: MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Model
• Authors: Yifei Chen, Sarra Habchi, Lili Wei,
• Abstract summary: MIMIC is a novel framework that integrates diverse personality traits into gaming agents.<n>It can achieve higher test coverage and richer in-game interactions across different games.<n>It also outperforms state-of-the-art agents in Minecraft by achieving a higher task completion rate.
• Score: 9.426130742272715
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Modern video games pose significant challenges for traditional automated testing algorithms, yet intensive testing is crucial to ensure game quality. To address these challenges, researchers designed gaming agents using Reinforcement Learning, Imitation Learning, or Large Language Models. However, these agents often neglect the diverse strategies employed by human players due to their different personalities, resulting in repetitive solutions in similar situations. Without mimicking varied gaming strategies, these agents struggle to trigger diverse in-game interactions or uncover edge cases. In this paper, we present MIMIC, a novel framework that integrates diverse personality traits into gaming agents, enabling them to adopt different gaming strategies for similar situations. By mimicking different playstyles, MIMIC can achieve higher test coverage and richer in-game interactions across different games. It also outperforms state-of-the-art agents in Minecraft by achieving a higher task completion rate and providing more diverse solutions. These results highlight MIMIC's significant potential for effective game testing.

Related papers

• FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games [56.81554611870848]
  We introduce FlashAdventure, a benchmark of 34 Flash-based adventure games designed to test full story arc completion.<n>We also propose CUA-as-a-Judge, an automated gameplay evaluator, and COAST, an agentic framework leveraging long-term clue memory.<n> Experiments show current GUI agents struggle with full story arcs, while COAST improves milestone completion by bridging the observation-behavior gap.
  arXiv  Detail & Related papers  (2025-09-01T01:33:16Z)
• Who's Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation [12.528928000871405]
  We consider a multi-agent setting where the goal is to identify the "worst offenders:" agents that are gaming most aggressively.<n>We introduce a framework in which each agent's tendency to game is parameterized via a scalar.<n>By recasting the problem as a causal effect estimation problem where different agents represent different "treatments," we prove that a ranking of all agents by their gaming parameters is identifiable.
  arXiv  Detail & Related papers  (2024-12-02T22:07:48Z)
• Expectation vs. Reality: Towards Verification of Psychological Games [18.30789345402813]
  Psychological games (PGs) were developed as a way to model and analyse agents with belief-dependent motivations. This paper proposes methods to solve PGs and implementing them within PRISM-games, a formal verification tool for games.
  arXiv  Detail & Related papers  (2024-11-08T14:41:52Z)
• Reinforcement Learning for High-Level Strategic Control in Tower Defense Games [47.618236610219554]
  In strategy games, one of the most important aspects of game design is maintaining a sense of challenge for players. We propose an automated approach that combines traditional scripted methods with reinforcement learning. Results show that combining a learned approach, such as reinforcement learning, with a scripted AI produces a higher-performing and more robust agent than using only AI.
  arXiv  Detail & Related papers  (2024-06-12T08:06:31Z)
• Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games [21.168085154982712]
  equilibria in multiplayer games are neither unique nor non-exploitable. This paper takes an initial step towards addressing these challenges by focusing on the natural objective of equal share. We design a series of efficient algorithms, inspired by no-regret learning, that provably attain approximate equal share across various settings.
  arXiv  Detail & Related papers  (2024-06-06T15:59:17Z)
• Preference-conditioned Pixel-based AI Agent For Game Testing [1.5059676044537105]
  Game-testing AI agents that learn by interaction with the environment have the potential to mitigate these challenges. This paper proposes an agent design that mainly depends on pixel-based state observations while exploring the environment conditioned on a user's preference. Our agent significantly outperforms state-of-the-art pixel-based game testing agents over exploration coverage and test execution quality when evaluated on a complex open-world environment resembling many aspects of real AAA games.
  arXiv  Detail & Related papers  (2023-08-18T04:19:36Z)
• Collusion Detection in Team-Based Multiplayer Games [57.153233321515984]
  We propose a system that detects colluding behaviors in team-based multiplayer games. The proposed method analyzes the players' social relationships paired with their in-game behavioral patterns. We then automate the detection using Isolation Forest, an unsupervised learning technique specialized in highlighting outliers.
  arXiv  Detail & Related papers  (2022-03-10T02:37:39Z)
• Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity [49.68758494467258]
  We study how to construct diverse populations of agents by carefully structuring how individuals within a population interact. Our approach is based on interaction graphs, which control the flow of information between agents during training. We provide evidence for the importance of diversity in multi-agent training and analyse the effect of applying different interaction graphs on the training trajectories, diversity and performance of populations in a range of games.
  arXiv  Detail & Related papers  (2021-10-08T11:29:52Z)
• Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents [137.86426963572214]
  We show how to combine distinct behavioral policies to obtain a meaningful "fusion" policy. We propose four different policy fusion methods for combining pre-trained policies. We provide several practical examples and use-cases for how these methods are indeed useful for video game production and designers.
  arXiv  Detail & Related papers  (2021-04-21T16:08:44Z)
• Generating Diverse and Competitive Play-Styles for Strategy Games [58.896302717975445]
  We propose Portfolio Monte Carlo Tree Search with Progressive Unpruning for playing a turn-based strategy game (Tribes) We show how it can be parameterized so a quality-diversity algorithm (MAP-Elites) is used to achieve different play-styles while keeping a competitive level of play. Our results show that this algorithm is capable of achieving these goals even for an extensive collection of game levels beyond those used for training.
  arXiv  Detail & Related papers  (2021-04-17T20:33:24Z)
• Griddly: A platform for AI research in games [0.0]
  We present Griddly as a new platform for Game AI research. Griddly provides a unique combination of highly customizable games, different observer types and an efficient C++ core engine. We present a series of baseline experiments to study the effect of different observation configurations and generalization ability of RL agents.
  arXiv  Detail & Related papers  (2020-11-12T13:23:31Z)
• The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition [14.726566410348985]
  The Multi-Agent Reinforcement Learning in Malm"O (MARL"O) competition is a new challenge that proposes research in this domain using multiple 3D games.<n>The goal of this contest is to foster research in general agents that can learn across different games and opponent types.
  arXiv  Detail & Related papers  (2019-01-23T21:01:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.