continuity-aware service personalization

Existing evaluations of personalized AI agents for information retrieval rely heavily on static benchmarks, failing to capture the temporal evolution of user needs and long-term interactive adaptability. To address this, we propose a novel dynamic, interaction-aware paradigm for longitudinal evaluation: (1) a time-varying preference modeling-based persona simulator; (2) a reference-interview-driven protocol for structured preference elicitation; and (3) cross-session behavioral adaptability metrics. Our method integrates large language model–driven user simulation, preference elicitation, and longitudinal interaction analysis. We conduct empirical evaluation in the e-commerce search setting using the PersonalWAB dataset. This work is the first to systematically define and empirically validate an evaluation framework for personalized agents’ *sustained adaptability*—a core capability for long-term user alignment. It establishes a reproducible, scalable theoretical and practical foundation for user-centered, longitudinal interaction optimization.

Existing LLM alignment methods focus on static, single-turn, or universal value alignment, failing to model users’ long-term personalized preferences and address cold-start challenges. This paper proposes PersonalAgent—the first proactive dialogue agent that formalizes cross-session personalization as a sequential reasoning task. It integrates LLM-driven dialogue decomposition, temporal preference modeling, dynamic user profile updating, and reinforcement learning–based policy optimization to track preference evolution and mitigate cold start. Its key innovation lies in establishing the first cross-session consistent sequential alignment framework, inherently robust to dialogue noise. Experiments demonstrate significant improvements over prompt-based and policy-optimization baselines under both ideal and noisy dialogue conditions. Human evaluation confirms that PersonalAgent achieves state-of-the-art performance in naturalness and consistency of preference understanding.

This study addresses the challenge that users often lack effective support in recognizing and evaluating personalization opportunities within self-directed interface customization, leading to underutilization of available features. To bridge this gap, the paper proposes a “reflexive personalization” approach that guides users to reflect on their own interaction data, thereby enhancing their awareness of personalization value, facilitating trade-off assessments between benefits and effort, and improving the transparency of system-generated suggestions. Through an exploratory design probe employing experimental scenario scripts, semi-structured interviews, and qualitative analysis with twelve participants, the research demonstrates that while users can independently identify personalization opportunities, they strongly prefer system-provided visual recommendations. Interaction data significantly strengthens users’ willingness to change, heightens their perception of data value, and refines their personalization decision-making process.

This work proposes an AI-driven approach to dynamic front-end personalization that overcomes the limitations of traditional static designs or rule-based systems, which often fail to accurately respond to user behavior. By leveraging a user behavior prediction model, the system dynamically adjusts interface layout and content in real time, while incorporating reinforcement learning to optimize the prioritization of functional elements. The architecture is designed to be scalable and adaptive, enabling efficient deployment and continuous iteration. Experimental results demonstrate that the proposed method significantly outperforms conventional rule-driven approaches in terms of user experience and interaction efficiency, thereby validating the effectiveness and practical value of integrating artificial intelligence into front-end personalization.

This work addresses the limitations of existing personalized services, which are typically confined to single platforms and unable to effectively integrate heterogeneous user data across multiple online platforms and offline contexts, resulting in incomplete user profiles. To overcome this challenge, the paper introduces a novel user-centric paradigm for cross-domain personalization that places the user at the center of the process. By leveraging readily available large language model (LLM) agents, the proposed approach intelligently reasons over and fuses multi-source data voluntarily exported by users themselves, thereby breaking down platform-specific data silos. Experimental results demonstrate that this method significantly outperforms baseline approaches relying solely on single-platform data, confirming the effectiveness and superiority of a user-controlled, boundary-spanning personalization system.

Existing lifelong personalization approaches rely on semantic similarity to assess relevance, struggling to extract critical user information from interaction histories that are topically unrelated yet contextually relevant. To address this limitation, this work introduces the LUCid benchmark—the first user-centric framework for evaluating contextual relevance—comprising 1,936 real-world queries paired with up to 500 rounds of historical conversations. Through comprehensive experiments across multiple architectures, the study systematically evaluates state-of-the-art models, including Gemini-3-Flash, GPT-5.4, and Claude Haiku, on retrieval recall and response alignment. Results reveal a stark performance gap: on the most challenging samples that are semantically distant yet contextually relevant, model recall approaches zero and response alignment hovers around 50%, exposing a fundamental misalignment between current relevance modeling capabilities and real-world user needs.

This study addresses critical limitations in existing user modeling approaches within model-driven engineering, including fragmentation, incomplete dimensional coverage, and weak dynamic evolution capabilities, compounded by a lack of effective tool support. To overcome these challenges, the authors propose a low-code-driven unified user modeling framework that integrates multidimensional domain knowledge to construct reusable user models. Leveraging machine learning, the framework enables dynamic, incremental updates and automatic adaptation of user profiles. Grounded in a systematic literature review, user behavior analysis, and automated pipeline technologies, this work not only identifies current modeling shortcomings but also outlines a technical roadmap for developing dynamic, comprehensive, and automated personalized dialogue systems, thereby establishing a novel paradigm for efficient personalization in intelligent agents.

This work addresses the scarcity of user customization in everyday productivity tools and the lack of flexible, natural language–based mechanisms for adapting system behavior. It proposes embedding generative AI–driven conversational customization into email systems, enabling users to iteratively reshape their inbox structure, interface, and workflows through natural language, thereby transforming static interfaces into malleable data layers. Through a user-centered design probe, the study reveals that users prefer adaptive modifications grounded in existing patterns over creating configurations from scratch. While such customization significantly enhances tool flexibility, it also introduces risks of misconfiguration, necessitating continuous oversight and iterative refinement mechanisms. The findings illuminate practical pathways and design implications for integrating conversational customization into routine productivity applications.