Scholarlink

<p>The rapid iteration cycles of modern live-service games make regression testing indispensable for maintaining quality and stability. However, existing regression testing approaches face critical limitations, especially in common gray-box settings where full source code access is unavailable: they heavily rely on manual effort for test case construction, struggle to maintain growing suites plagued by redundancy, and lack efficient mechanisms for prioritizing relevant tests. These challenges result in excessive testing costs, limited automation, and insufficient bug detection. To address these issues, we propose <span>SAGE</span>, a semantic-aware regression testing framework for gray-box game environments. <span>SAGE</span> systematically addresses the core challenges of test generation, maintenance, and selection. It employs LLM-guided reinforcement learning for efficient, goal-oriented exploration to automatically generate a diverse foundational test suite. Subsequently, it applies a semantic-based multi-objective optimization to refine this suite into a compact, high-value subset by balancing cost, coverage, and rarity. Finally, it leverages LLM-based semantic analysis of update logs to prioritize test cases most relevant to version changes, enabling efficient adaptation across iterations. We evaluate <span>SAGE</span> on two representative environments, Overcooked Plus and Minecraft, comparing against both automated baselines and human-recorded test cases. Across all environments, <span>SAGE</span> achieves superior bug detection with significantly lower execution cost, while demonstrating strong adaptability to version updates.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SAGE: Semantic-aware gray-box game regression testing with large language models

  • 期刊论文

  • 发表日期：

    2026年7月29日

查看全文
  • Jinyu Cai,
  • Jialong Li,
  • Nianyu Li,
  • Zhenyu Mao,
  • Mingyue Zhang,
  • Kenji Tei

摘要

The rapid iteration cycles of modern live-service games make regression testing indispensable for maintaining quality and stability. However, existing regression testing approaches face critical limitations, especially in common gray-box settings where full source code access is unavailable: they heavily rely on manual effort for test case construction, struggle to maintain growing suites plagued by redundancy, and lack efficient mechanisms for prioritizing relevant tests. These challenges result in excessive testing costs, limited automation, and insufficient bug detection. To address these issues, we propose SAGE, a semantic-aware regression testing framework for gray-box game environments. SAGE systematically addresses the core challenges of test generation, maintenance, and selection. It employs LLM-guided reinforcement learning for efficient, goal-oriented exploration to automatically generate a diverse foundational test suite. Subsequently, it applies a semantic-based multi-objective optimization to refine this suite into a compact, high-value subset by balancing cost, coverage, and rarity. Finally, it leverages LLM-based semantic analysis of update logs to prioritize test cases most relevant to version changes, enabling efficient adaptation across iterations. We evaluate SAGE on two representative environments, Overcooked Plus and Minecraft, comparing against both automated baselines and human-recorded test cases. Across all environments, SAGE achieves superior bug detection with significantly lower execution cost, while demonstrating strong adaptability to version updates.