{"ID":2870589,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.13444","arxiv_id":"2509.13444","title":"DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces","abstract":"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.","short_abstract":"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 tha...","url_abs":"https://arxiv.org/abs/2509.13444","url_pdf":"https://arxiv.org/pdf/2509.13444v2","authors":"[\"Yuan Xu\",\"Shaowen Xiang\",\"Yizhi Song\",\"Ruoting Sun\",\"Xin Tong\"]","published":"2025-09-16T18:24:42Z","proceeding":"cs.HC","tasks":"[\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}