arXiv subjects

Yusei Ishimizu

Publications and source records attributed to Yusei Ishimizu.

3 recordsLinked to original sources

arXiv2026

Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithms

Social media platforms frequently impose restrictive policies to moderate user content, prompting the emergence of creative evasion language strategies. This paper presents a multi-agent framework based on Large Language Models (LLMs) to simulate the iterative evolution of language strategies under regulatory constraints. In this framework, participant agents, as social media users, continuously evolve their language expression, while supervisory agents emulate platform-level regulation by assessing policy violations. To achieve a more faithful simulation, we employ a dual design of language strategies (constraint and expression) to differentiate conflicting goals and utilize an LLM-driven GA (Genetic Algorithm) for the selection, mutation, and crossover of language strategies. The framework is evaluated using two distinct scenarios: an abstract password game and a realistic simulated illegal pet trade scenario. Experimental results demonstrate that as the number of dialogue rounds increases, both the number of uninterrupted dialogue turns and the accuracy of information transmission improve significantly. Furthermore, a user study with 40 participants validates the real-world relevance of the generated dialogues and strategies. Moreover, ablation studies validate the importance of the GA, emphasizing its contribution to long-term adaptability and improved overall results.

cs.SI↗

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

Automatic Adaptation Rule Optimization via Large Language Models

Rule-based adaptation is a foundational approach to self-adaptation, characterized by its human readability and rapid response. However, building high-performance and robust adaptation rules is often a challenge because it essentially involves searching the optimal design in a complex (variables) space. In response, this paper attempt to employ large language models (LLMs) as a optimizer to construct and optimize adaptation rules, leveraging the common sense and reasoning capabilities inherent in LLMs. Preliminary experiments conducted in SWIM have validated the effectiveness and limitation of our method.

cs.CL↗