Selected work

Representative Papers

Interaction-Driven Browsing: A Human-in-the-Loop Conceptual Framework Informed by Human Web Browsing for Browser-Using Agents

Sep 15, 2025

Existing browser user agents (BUAs) operate in a single-step, instruction-driven manner, rendering them inadequate for complex, nonlinear browsing tasks involving ambiguous user goals, iterative decision-making, and dynamically evolving contextual information. Method: This paper proposes a human–computer collaborative browser agent framework inspired by theories of human browsing behavior. It establishes an “action–feedback–reasoning” closed-loop architecture that explicitly distinguishes exploratory from exploitative actions, enabling progressive navigation and real-time policy adaptation. Crucially, it systematically integrates cognitive behavioral models into agent design and adopts a human-in-the-loop (HITL) architecture to support interaction-driven browsing. Contribution/Results: Evaluated across diverse hypothetical use cases, the framework significantly reduces both user operational and cognitive load while enhancing process controllability and robustness in goal achievement. It advances browser agents from passive command executors toward proactive, adaptive collaborators.

0 citationsRead paper

UX Remix: Improving Measurement Item Design Process Using Large Language Models and Prior Literature

Apr 12, 2025

HCI scale development has long suffered from nonstandardized processes, poor construct-theory alignment, and low item reuse rates. This paper introduces the first interactive support system integrating large language models (LLMs) with a structured, empirically grounded measurement knowledge base, enabling a closed-loop workflow: construct identification → theory-informed custom definition → context-aware item generation. The system retrieves theoretically appropriate constructs from a literature-anchored database and leverages LLMs to generate semantically coherent, domain-specific items, supporting human-AI co-refinement. Its key innovation lies in the deep coupling of LLMs with an evidence-validated construct–item relational database, shifting scale development from experience-driven practice toward evidence-enhanced collaborative measurement. Experiments show a 62% reduction in design time, a 3.1× increase in item reuse, and significantly improved theoretical fidelity; expert evaluations across multiple rounds confirm ≥92% contextual appropriateness. The system has been integrated into a prototype HCI research workflow.

0 citationsRead paper

Recent publications

Latest Papers

Interaction-Driven Browsing: A Human-in-the-Loop Conceptual Framework Informed by Human Web Browsing for Browser-Using Agents

Sep 15, 2025

Existing browser user agents (BUAs) operate in a single-step, instruction-driven manner, rendering them inadequate for complex, nonlinear browsing tasks involving ambiguous user goals, iterative decision-making, and dynamically evolving contextual information. Method: This paper proposes a human–computer collaborative browser agent framework inspired by theories of human browsing behavior. It establishes an “action–feedback–reasoning” closed-loop architecture that explicitly distinguishes exploratory from exploitative actions, enabling progressive navigation and real-time policy adaptation. Crucially, it systematically integrates cognitive behavioral models into agent design and adopts a human-in-the-loop (HITL) architecture to support interaction-driven browsing. Contribution/Results: Evaluated across diverse hypothetical use cases, the framework significantly reduces both user operational and cognitive load while enhancing process controllability and robustness in goal achievement. It advances browser agents from passive command executors toward proactive, adaptive collaborators.

0 citationsRead paper

UX Remix: Improving Measurement Item Design Process Using Large Language Models and Prior Literature

Apr 12, 2025

HCI scale development has long suffered from nonstandardized processes, poor construct-theory alignment, and low item reuse rates. This paper introduces the first interactive support system integrating large language models (LLMs) with a structured, empirically grounded measurement knowledge base, enabling a closed-loop workflow: construct identification → theory-informed custom definition → context-aware item generation. The system retrieves theoretically appropriate constructs from a literature-anchored database and leverages LLMs to generate semantically coherent, domain-specific items, supporting human-AI co-refinement. Its key innovation lies in the deep coupling of LLMs with an evidence-validated construct–item relational database, shifting scale development from experience-driven practice toward evidence-enhanced collaborative measurement. Experiments show a 62% reduction in design time, a 3.1× increase in item reuse, and significantly improved theoretical fidelity; expert evaluations across multiple rounds confirm ≥92% contextual appropriateness. The system has been integrated into a prototype HCI research workflow.

0 citationsRead paper