This research focuses on leveraging Large Language Models (LLMs) to automate and streamline the design and optimization of self-adaptive systems. Traditionally, creating effective adaptation rules has been a significant challenge, relying on costly, manual, trial-and-error processes conducted by domain experts. Furthermore, a critical gap exists where modern LLM-driven adaptation methods cannot be directly applied to or evaluated with the vast number of existing research artifacts (testbeds), hindering progress.To address these challenges, this year's research yielded two primary contributions. First, we proposed LLM-ARG, a novel framework for the automatic generation and optimization of adaptation rules. LLM-ARG operates in an iterative loop: it analyzes system execution history to identify performance issues within the current rules, proposes semantic improvements to the underlying state-space design, and automatically generates the revised source code. Through experiments on a server load-balancing scenario, we demonstrated that LLM-ARG can achieve performance comparable to human-designed rules while significantly reducing design time and cost. Second, to bridge the gap between LLMs and existing research infrastructure, we developed a customizable and well-informed wrapper. This platform specifically addresses two fundamental issues: (1) Domain-grounding, by establishing an explicit domain knowledge base to prevent LLMs from generating unrealistic or impractical commands; and (2) Well-informing, by creating a runtime observation base to provide LLMs with comprehensive, real-time system data. This wrapper facilitates the integration of LLMs with legacy artifacts, enabling researchers to leverage existing assets for developing and validating new adaptation strategies. We have successfully implemented and released this wrapper for three renowned artifacts (Znn.com, DeltaIoT, and TAS), providing a practical tool that has been accepted and published at an international conference.

人間と協調作業するソフトウェアシステムを設計する際に、人間とシステムそれぞれが果たすべき責務の明確化が求められる。高度な協調作業を実現するには、責務が動作環境に応じて変化・適応する必要がある。従来の研究では、責務（要求・要件とそれを実現するエージェントの対応関係）は開発時に決められた以降固定的なものとして扱われており、実行中に環境に応じて変更・適応(adaptation)する動的な要素として扱われていない。責務を動的な要素として扱うには、動作環境の変化を開発時に想定し尽くし、あらゆる動作環境にも対処できる適応ルールを開発時に準備するのは困難である。本研究は、動作環境コンテキストとシステムの各側面を表現するモデル（要求モデル、動作仕様モデル）など実行時の情報を活用し、実行時に適切な責務を推論することで、実行時に責務の適応を実現するフレームワークを提案する。本年度では、複数分析粒度を活用した推論手法を提案し、色弱者サポートなど実アプリへの応用を試みた。

Our research project has achieved breakthroughs in optimizing the collaboration between humans and robots. Our work involved several key studies:1) We developed a method for improving user satisfaction in human-robot collaborative tasks by analyzing user complaints to infer and adapt the system's behavior and responsibilities. This approach led to an increase in user satisfaction during tasks involving robots and humans. Our findings were published in the 18th Symposium on Software Engineering for Adaptive and Self-Managing Systems, with the paper titled "Preference Adaptation: User Satisfaction Is All You Need!"2) In a warehouse delivery scenario, we showcased an adaptive robot controlled through Discrete Controller Synthesis. This robot was able to adjust its goals and responsibilities in real-time in response to changes in the external environment, including human workers. The results of this study were presented at the 4th IEEE International Conference on Autonomic Computing and Self-Organizing Systems, in a paper titled "Demonstration of a Real-world Self-adaptive Robot Path-finding using Discrete Controller Synthesis."23) Focusing on autonomous driving scenarios, we analyzed users' perceptual and emotional safety as a responsibility of the system in collaborative tasks. Our aim was to enhance the subjective safety of humans in these operations. This research was featured in the 23rd International Conference on Intelligent Systems Design and Applications, with the paper titled "Towards Enhancing Driver's Perceived Safety in Autonomous Driving: A Shield-based Approach."4) We also focused on Systems-of-Systems, where system architecture and environments are highly variable. By applying Discrete Controller Synthesis in Systems-of-Systems, we laid the groundwork for future research on responsibility distribution in large-scale systems. This study will be published in the 12th ACM/IEEE International Workshop on Software Engineering for Systems-of-Systems and Software Ecosystems, with the paper titled "Employing Discrete Controller Synthesis for Developing Systems-of-Systems Controllers."Overall, our project contributed to the field of human-robot collaboration by developing innovative methods for the dynamic distribution of responsibilities, enhancing user satisfaction, safety, and efficiency in various applications.