arXiv subjects

Yuya Miyaoka

Publications and source records attributed to Yuya Miyaoka.

5 recordsLinked to original sources

arXiv2026

Agentic MPC for Semantic Control System Resynthesis

While MPC effectively handles structured, diverse, and low-level specifications, it lacks the capability to dynamically incorporate high-level contextual information such as social norms, user intent, or natural language instructions. To address this limitation, this manuscript introduces an agentic MPC framework that enables context-aware, semantically adaptive control synthesis by integrating with large language model-based agents. The agent interprets heterogeneous inputs, including natural language messages, environmental observations, and external knowledge, to resynthesize the control specifications. The effectiveness of the framework is demonstrated in an autonomous driving scenario, where the system aligns with personal preferences or responds to social situations such as emergency vehicle yielding.

eess.SY↗

arXiv2025

Chat-Driven Optimal Management for Virtual Network Services

This paper proposes a chat-driven network management framework that integrates natural language processing (NLP) with optimization-based virtual network allocation, enabling intuitive and reliable reconfiguration of virtual network services. Conventional intent-based networking (IBN) methods depend on statistical language models to interpret user intent but cannot guarantee the feasibility of generated configurations. To overcome this, we develop a two-stage framework consisting of an Interpreter, which extracts intent from natural language prompts using NLP, and an Optimizer, which computes feasible virtual machine (VM) placement and routing via an integer linear programming. In particular, the Interpreter translates user chats into update directions, i.e., whether to increase, decrease, or maintain parameters such as CPU demand and latency bounds, thereby enabling iterative refinement of the network configuration. In this paper, two intent extractors, which are a Sentence-BERT model with support vector machine (SVM) classifiers and a large language model (LLM), are introduced. Experiments in single-user and multi-user settings show that the framework dynamically updates VM placement and routing while preserving feasibility. The LLM-based extractor achieves higher accuracy with fewer labeled samples, whereas the Sentence-BERT with SVM classifiers provides significantly lower latency suitable for real-time operation. These results underscore the effectiveness of combining NLP-driven intent extraction with optimization-based allocation for safe, interpretable, and user-friendly virtual network management.

cs.NI↗

arXiv2025

Chat-Driven Reconfiguration of Model Predictive Control

Traditional control personalization requires users to understand optimization parameters and provide repetitive numerical feedback, creating significant barriers for non-expert users. To deal with this issue, we propose ChatMPC, a model predictive control framework that enables users to personalize control systems and adapt to environmental changes through natural language interaction. The framework operates in two modes: personalization, where users iteratively adjust control behavior to their preferences, and co-development, where users provide real-time environmental information that complements sensor data. We establish convergence guarantees under different user behavior models, demonstrating exponential convergence for consistent feedback and finite-time convergence with logarithmic interaction complexity for tolerance-based users. We validate ChatMPC through experiments in robot navigation with personalized obstacle avoidance and semi-autonomous driving with conversational obstacle reporting. Both experiments achieve real-time performance and demonstrate effective adaptation to user preferences and environmental changes.

eess.SY↗

arXiv2024

CBF-LLM: Safe Control for LLM Alignment

This paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The presented framework applies the safety filter, designed based on the CBF, to the output generation of the baseline LLM, i.e., the sequence of the token, with the aim of intervening in the generated text. The overall text-generation system is implemented with Llama 3 and a RoBERTa model, and the source code is available at https://github.com/Mya-Mya/CBF-LLM. The experiment demonstrates its control ability and effectiveness in reducing the number of interventions needed for user-specified alignment tasks.

eess.SY↗

arXiv2023

ChatMPC: Natural Language based MPC Personalization

We address the personalization of control systems, which is an attempt to adjust inherent safety and other essential control performance based on each user's personal preferences. A typical approach to personalization requires a substantial amount of user feedback and data collection, which may result in a burden on users. Moreover, it might be challenging to collect data in real-time. To overcome this drawback, we propose a natural language-based personalization, which places a comparatively lighter burden on users and enables the personalization system to collect data in real-time. In particular, we consider model predictive control (MPC) and introduce an approach that updates the control specification using chat within the MPC framework, namely ChatMPC. In the numerical experiment, we simulated an autonomous robot equipped with ChatMPC. The result shows that the specification in robot control is updated by providing natural language-based chats, which generate different behaviors.

cs.HC↗