conversational co-design

Human-AI conversational interfaces face design challenges stemming from ambiguous user goals, users’ limited awareness of AI capabilities, and the transient, ephemeral nature of interactions. Method: This study proposes an AI-agent-driven CHAI (Conversational Human-AI Interaction) workflow, positioning AI as a collaborative design partner to support real-time prompt generation, user-agent simulation testing, and goal-clarification scaffolding. Developed through four iterative cycles and empirically validated with 10 users, the workflow integrates design probes, thematic analysis, and contextualized prompt engineering. Contribution/Results: We deliver an interpretable prototype suite and introduce the first reusable CHAI agent workflow paradigm under a “research-through-design” framework. Evaluation shows significant improvements in user goal articulation (+42%) and feedback depth. Additionally, we establish a curated, annotated design asset library comprising 12 canonical interaction patterns, enabling high-fidelity early-stage CHAI experience validation.

This work proposes a multimodal learning framework based on adaptive context fusion to address the limited generalization of existing methods in complex scenarios. The approach dynamically aligns visual and linguistic features and incorporates a lightweight gating mechanism to enable efficient cross-modal integration. Experimental results demonstrate that the model significantly outperforms current state-of-the-art methods across multiple benchmark datasets, achieving improvements of 3.2% in accuracy and 5.7% in robustness. The primary contribution lies in the design of a scalable fusion architecture that effectively mitigates the semantic gap between modalities, offering a novel technical pathway for multimodal understanding tasks.

Large language models (LLMs) exhibit unstable dialogue behavior and poor maintainability in complex business processes. Method: This paper proposes Conversation Routines (CR), a framework that formalizes task-oriented dialogue logic via natural-language specifications, pioneering the integration of structured business workflows directly into LLM prompts—thereby decoupling dialogue design from tool implementation. CR supports modular routine definition and composition, natural-language-driven workflow orchestration, and synergistically combines tool-augmented conversational agents (Tool-Augmented CAS) with prompt engineering. Contribution/Results: Evaluated on two proof-of-concept scenarios—train ticket booking and interactive fault diagnosis—CR enables domain experts to build high-fidelity, high-task-success-rate dialogues without coding. It significantly improves system interpretability, reusability, and cross-role collaboration efficiency.

In asynchronous collaborative creativity, the absence of sustained human guidance leads to inefficiencies in idea generation and evaluation. Method: This study proposes a dual-modal collaborative chatbot framework comprising one agent specialized in divergent ideation and another in convergent evaluation. It pioneers the systematic modeling of human guidance expertise as asynchronously executable dialogue strategies, integrating human factors–driven structured workflows, personalized prompt engineering, and an expert feedback loop. Results: A user study with 48 participants demonstrates statistically significant improvements (p < 0.01) in cross-temporal idea co-construction quality and convergence efficiency. Expert evaluation confirms feasibility but highlights the need for enhanced human–AI collaboration to improve social presence. The core contribution is the first fully automated, dynamically adaptive asynchronous creativity guidance paradigm that supports end-to-end creative processes while accommodating individual pacing.

This paper addresses the challenge of operationalizing generative AI within collaborative software engineering teams. Drawing on a design study with 39 industry experts—including field observations, semi-structured interviews, and multi-role workshops—we systematically investigate how prompt engineering supports cross-functional AI prototyping and iterative co-design. Our study is the first to characterize three core phenomena in collaborative prompt prototyping: (1) the emergent construction of shared coordination norms, (2) dynamic role evolution across developers, domain experts, and AI specialists, and (3) context-sensitive evaluation mechanisms for prompt efficacy. We propose a generative-content-feature-driven rapid iteration paradigm and distill a reusable prompt prototyping strategy framework. Key technical challenges—including model opacity and example overfitting—are empirically identified. The findings provide both methodological grounding and actionable practice guidelines for industrial software teams, advancing the shift from generative AI as a technical capability to a collaborative design enabler.

This study addresses the challenge of sparse and low-quality user feedback during interactions with conversational agents, which hinders effective human-AI collaboration and model improvement. Grounded in Grice’s maxims of conversation, the authors conduct two qualitative user studies to systematically identify four key barriers that impede high-quality feedback. Building on these insights, they propose three actionable design principles and integrate them with a feedback scaffolding mechanism to develop a supportive interaction prototype. Experimental evaluation demonstrates that systems adhering to these design guidelines significantly enhance the quality of user feedback. This work presents the first systematic taxonomy of feedback barriers and introduces a novel paradigm for large language models to proactively elicit more effective user feedback.

Misinterpretation of client requirements in design practice leads to significant resource waste. Method: This study proposes a digital requirements elicitation method integrating conversational AI with a choice-based response mechanism to enhance requirement alignment efficiency during early client–designer collaboration. A three-phase empirical investigation—including a 2×2 factorial experiment, semi-structured interviews, and the User Experience Questionnaire (UEQ)—was conducted; notably, this work pioneers the integration of structured responses into conversational AI interactions to establish a bidirectional, collaborative requirements elicitation paradigm. Contribution/Results: The method significantly improves the clarity of client inputs and accuracy of requirement articulation, while strengthening both parties’ readiness for early-stage collaboration. Although it slightly reduces perceived system dependence, it overall enhances both the quality and efficiency of requirements elicitation. The study delivers a reusable methodology and tool framework for human–AI collaborative requirements engineering in professional design domains.

This study investigates how conversational AI can effectively support preparation for high-stakes workplace negotiations while mitigating its potential interference with users’ cognitive processes and strategic reasoning. Through the development of Trucey—a theory-driven AI coaching system—and a preregistered controlled experiment complemented by user interviews and cognitive load assessments, the research uncovers a fundamental mismatch between the linear interaction patterns of conversational AI and the inherently recursive nature of negotiation tasks. The work proposes a phased coaching design principle—“map first, then path, then simulate”—and identifies overlooked boundary conditions in human-AI collaboration. Empirical findings reveal that a static manual outperformed AI-based support in perceived empowerment and usability, with none of the four core design hypotheses supported, thereby highlighting the current limitations of conversational AI in handling recursively complex tasks.

Domain-specific chatbots suffer from ambiguous user intent, contextual fragmentation, and interaction disorganization during multi-turn interactions—such as conditional filtering, multi-option selection, and comparative operations—due to the absence of GUI-like “submit/reset” mechanisms. To address this, this work introduces, for the first time, a form-based Submit/Reset paradigm into conversational systems, explicitly modeling user confirmation behaviors and context-switching actions. Methodologically, we integrate formalized state tracking, fine-grained user action recognition, and chain-of-thought (CoT) reasoning, augmented by prompt engineering to enhance large language models’ capacity for structured dialogue state representation. Experiments in hotel booking and customer management domains demonstrate significant improvements: +28.6% in multi-turn task coherence, +32.1% in user satisfaction, and a reduction of 2.4 turns on average, indicating enhanced operational efficiency.

In face-to-face small-group conversations, participants often struggle to simultaneously manage attention allocation, interpret nonverbal cues, and engage effectively due to a lack of real-time informational support. This study systematically investigates the design requirements and opportunities for proactive information support through focus groups and two mixed-reality technology probes, employing participatory design and qualitative methods. It presents the first set of design principles specifically tailored for proactive information support in small-group dialogues and identifies key design opportunities that maximize its benefits. The findings offer a novel paradigm for developing proactive AI agents in augmented reality and lay the groundwork for enriched, augmented face-to-face conversational experiences.