arXiv subjects

Takuto Yamauchi

Publications and source records attributed to Takuto Yamauchi.

3 recordsLinked to original sources

arXiv2025

Graph Contextual Reinforcement Learning for Efficient Directed Controller Synthesis

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.

cs.AI↗

arXiv2025

Automatic Syntax Error Repair for Discrete Controller Synthesis using Large Language Model

Discrete Controller Synthesis (DCS) is a powerful formal method for automatically generating specifications of discrete event systems. However, its practical adoption is often hindered by the highly specialized nature of formal models written in languages such as FSP and FLTL. In practice, syntax errors in modeling frequently become an important bottleneck for developers-not only disrupting the workflow and reducing productivity, but also diverting attention from higher-level semantic design. To this end, this paper presents an automated approach that leverages Large Language Models (LLMs) to repair syntax errors in DCS models using a well-designed, knowledge-informed prompting strategy. Specifically, the prompting is derived from a systematic empirical study of common error patterns, identified through expert interviews and student workshops. It equips the LLM with DCS-specific domain knowledge, including formal grammar rules and illustrative examples, to guide accurate corrections. To evaluate our method, we constructed a new benchmark by systematically injecting realistic syntax errors into validated DCS models. The quantitative evaluation demonstrates the high effectiveness of the proposed approach in terms of repair accuracy and its practical utility regarding time, achieving a speedup of 3.46 times compared to human developers. The experimental replication suite, including the benchmark and prompts, is available at https://github.com/Uuusay1432/DCSModelRepair.git

cs.SE↗

arXiv2024

Towards Context-aware Support for Color Vision Deficiency: An Approach Integrating LLM and AR

People with color vision deficiency often face challenges in distinguishing colors such as red and green, which can complicate daily tasks and require the use of assistive tools or environmental adjustments. Current support tools mainly focus on presentation-based aids, like the color vision modes found in iPhone accessibility settings. However, offering context-aware support, like indicating the doneness of meat, remains a challenge since task-specific solutions are not cost-effective for all possible scenarios. To address this, our paper proposes an application that provides contextual and autonomous assistance. This application is mainly composed of: (i) an augmented reality interface that efficiently captures context; and (ii) a multi-modal large language model-based reasoner that serves to cognitize the context and then reason about the appropriate support contents. Preliminary user experiments with two color vision deficient users across five different scenarios have demonstrated the effectiveness and universality of our application.

cs.CV↗