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

2025-12-14

AI Summary

Existing automated game testing approaches suffer from a disconnect between structural coverage (code-centric) and functional validation (player-centric). This paper addresses the challenge of service-oriented game updates by proposing a novel test framework that synergistically integrates structural mapping with functional guidance. Our method pioneers the joint use of abstract syntax tree (AST)-based semantic difference analysis and a context-aware hybrid reward mechanism, enabling dynamic balancing between code-branch exploration and high-level task completion. It unifies large language models (LLMs), AST analysis, reinforcement learning (RL), and game environment simulation (Overcooked/Minecraft). Experimental results demonstrate that our approach achieves over 94% branch coverage on code changes—nearly doubling that of conventional RL-based methods—while maintaining a 98% task success rate. This significantly enhances both the effectiveness and trustworthiness of update testing in live game services.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Bridges gap between code coverage and gameplay intent
• Automates testing for frequent game content updates
• Balances structural verification with functional validation

Innovation

• LLM interprets AST differences for intent extraction
• Hybrid reward mechanism guides RL agents adaptively
• Balances code coverage with gameplay task completion