Enhong Mu

Toshihide Ubukata, Enhong Mu, Takuto Yamauchi et al.

Controller synthesis is a formal method approach for automatically generating Labeled Transition System (LTS) controllers that satisfy specified properties. The efficiency of the synthesis process, however, is critically dependent on exploration policies. These policies often rely on fixed rules or strategies learned through reinforcement learning (RL) that consider only a limited set of current features. To address this limitation, this paper introduces GCRL, an approach that enhances RL-based methods by integrating Graph Neural Networks (GNNs). GCRL encodes the history of LTS exploration into a graph structure, allowing it to capture a broader, non-current-based context. In a comparative experiment against state-of-the-art methods, GCRL exhibited superior learning efficiency and generalization across four out of five benchmark domains, except one particular domain characterized by high symmetry and strictly local interactions.

Toshihide Ubukata, Zhiyao Wang, Enhong Mu et al.

On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement learning (RL) approaches learn such policies and achieve promising zero-shot generalization from small training instances to larger unseen ones. However, a fundamental limitation is anisotropic generalization, where an RL policy exhibits strong performance only in a specific region of the domain-parameter space while remaining fragile elsewhere due to training stochasticity and trajectory-dependent bias. To address this, we propose a Soft Mixture-of-Experts framework that combines multiple RL experts via a prior-confidence gating mechanism and treats these anisotropic behaviors as complementary specializations. The evaluation on the Air Traffic benchmark shows that Soft-MoE substantially expands the solvable parameter space and improves robustness compared to any single expert.

Enhong Mu, Jinyu Cai, Yijun Lu et al.

The rapid iteration and frequent updates of modern video games pose significant challenges to the efficiency and specificity of testing. Although automated playtesting methods based on Large Language Models (LLMs) have shown promise, they often lack structured knowledge accumulation mechanisms, making it difficult to conduct precise and efficient testing tailored for incremental game updates. To address this challenge, this paper proposes a KLPEG framework. The framework constructs and maintains a Knowledge Graph (KG) to systematically model game elements, task dependencies, and causal relationships, enabling knowledge accumulation and reuse across versions. Building on this foundation, the framework utilizes LLMs to parse natural language update logs, identify the scope of impact through multi-hop reasoning on the KG, enabling the generation of update-tailored test cases. Experiments in two representative game environments, Overcooked and Minecraft, demonstrate that KLPEG can more accurately locate functionalities affected by updates and complete tests in fewer steps, significantly improving both playtesting effectiveness and efficiency.

Enhong Mu, Minami Yoda, Yan Zhang et al.

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.