Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Yuan, Xiang, Shaowen, Song, Yizhi, Sun, Ruoting, Tong, Xin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.13444
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911445723119616
author Xu, Yuan
Xiang, Shaowen
Song, Yizhi
Sun, Ruoting
Tong, Xin
author_facet Xu, Yuan
Xiang, Shaowen
Song, Yizhi
Sun, Ruoting
Tong, Xin
contents Large Language Models are reshaping task automation, yet remain limited in complex, multi-step real-world tasks that require aligning with vague user intent and enabling dynamic user override. From a formative study with 12 participants, we found that end-users actively seek to shape task-oriented interfaces rather than relying on one-shot outputs. To address this, we introduce the human-agent co-generation paradigm, materialized in DuetUI. This LLM-empowered system unfolds alongside task progress through a bidirectional context loop-the agent scaffolds the interface by decomposing the task, while the user's direct manipulations implicitly steer the agent's next generation step. In a technical ablation study and a user study with 24 participants, DuetUI improved task efficiency and interface usability, supporting more seamless human-agent collaboration. Our contributions include the proposal of this novel paradigm, the design of a proof-of-concept DuetUI prototype embodying it, and empirical and technical insights from an initial evaluation of how this bidirectional loop may help align agents with human intent and inform future development.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13444
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces
Xu, Yuan
Xiang, Shaowen
Song, Yizhi
Sun, Ruoting
Tong, Xin
Human-Computer Interaction
Large Language Models are reshaping task automation, yet remain limited in complex, multi-step real-world tasks that require aligning with vague user intent and enabling dynamic user override. From a formative study with 12 participants, we found that end-users actively seek to shape task-oriented interfaces rather than relying on one-shot outputs. To address this, we introduce the human-agent co-generation paradigm, materialized in DuetUI. This LLM-empowered system unfolds alongside task progress through a bidirectional context loop-the agent scaffolds the interface by decomposing the task, while the user's direct manipulations implicitly steer the agent's next generation step. In a technical ablation study and a user study with 24 participants, DuetUI improved task efficiency and interface usability, supporting more seamless human-agent collaboration. Our contributions include the proposal of this novel paradigm, the design of a proof-of-concept DuetUI prototype embodying it, and empirical and technical insights from an initial evaluation of how this bidirectional loop may help align agents with human intent and inform future development.
title DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces
topic Human-Computer Interaction
url https://arxiv.org/abs/2509.13444