Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning

TL;DR

This paper introduces SMART, a framework that combines code coverage and gameplay intent understanding using LLM-guided reinforcement learning to improve automated game testing, especially for game updates.

Contribution

SMART uniquely integrates structural code analysis with gameplay intent via LLMs, enhancing testing coverage and functional validation in game development.

Findings

Achieves over 94% branch coverage of modified code

Nearly doubles coverage compared to traditional RL methods

Maintains 98% task completion rate in testing environments

Abstract

The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution to cope with this demanding release cadence. However, existing automated testing approaches typically create a dichotomy: code-centric methods focus on structural coverage without understanding gameplay context, while player-centric agents validate high-level intent but often fail to cover specific underlying code changes. To bridge this gap, we propose SMART (Structural Mapping for Augmented Reinforcement Testing), a novel framework that synergizes structural verification and functional validation for game update testing. SMART leverages large language models (LLMs) to interpret abstract syntax tree (AST) differences and extract functional intent, constructing a context-aware hybrid reward mechanism. This mechanism guides reinforcement learning agents to sequentially fulfill gameplay goals while adaptively exploring modified code branches. We evaluate SMART on two environments, Overcooked and Minecraft. The results demonstrate that SMART significantly outperforms state-of-the-art baselines; it achieves over 94% branch coverage of modified code, nearly double that of traditional reinforcement learning methods, while maintaining a 98% task completion rate, effectively balancing structural comprehensiveness with functional correctness.