TRUST-CUA @ IUI 2026 brings together researchers and practitioners in AI, HCI, and enterprise automation to explore trustworthy, transparent, and human-centered interfaces for generalist agents. The workshop builds on the growing ecosystem of CUA research and invites submissions that bridge technical, behavioral, and design perspectives.
We welcome submissions that investigate any aspect of trust, oversight, and user interaction in computer-using agents, including but not limited to:
Design & Evaluation Methods: participatory design for trustworthy agents; human-centered evaluation frameworks; inclusive and accessible agentic UIs across modalities.
Trustworthy & Explainability: safe execution, explainability and recovery workflows, transparency dashboards, rollback and undo, and reliable long-horizon behavior.
Human–Agent Interaction: interactive sandboxes and simulators; human-in-the-loop evaluation and alignment of agent behaviors, approval checkpoints, interactive debugging, provenance and uncertainty visualization, and risk communication.
Governance & Oversight: policy adherence, least-privilege consent, audit and compliance interfaces, and organizational red-teaming practices.
Adaptation & Learning: safe feedback-driven learning, configuration tuning under UX or policy constraints, and modular agent customization through user data or preferences.
Evaluation & Real-World Evidence: user-centered metrics for predictability and oversight, reproducibility artifacts, deployment studies, and incident analysis.
Foundations & Methods: planning and decision-making for controllability and explanation, and HCI methods for agentic UX research.
Empirical Studies & UX of Agents: observational and experimental studies of human–agent interaction; cognitive and affective aspects of agent UX
We invite three types of contributions:
Industry and innovation talk (up to 1 page)
A concise summary introducing a topic of interest, its relevance to the workshop theme, and the presenter’s experience and perspective on that topic.
Demos & Design Artifacts (up to 3 pages and/or a video)
Interactive prototypes, visualization tools, datasets, or conceptual designs that illustrate methods for explainability, safety, or oversight in CUAs.
Short Papers (up to 6 pages)
Empirical, theoretical, or design-driven contributions that present original ideas, frameworks, evaluations, or early-stage studies on trustworthy CUAs.
Submissions may describe ongoing work, emerging ideas, critical perspectives, or lessons learned from real-world deployments. Interdisciplinary contributions that connect AI, UX, and organizational practice are especially encouraged.
All accepted papers are expected to be presented at the conference, and at least one author is required to register to the conference.
Submissions should be single-blind so the names of the authors will be visible to the reviewers and should be indicated on the submitted files. In justified cases, if you wish your submission to be handled anonymously (i.e., double-blind) please send an e-mail to the workshop organizers. You will receive instructions on how to proceed.
participants and authors will be invited to contribute to:
TRUST-CUA Checklist v1.0: a shared best-practice framework for designing trustworthy CUAs.
CUBench-IUI: an emerging benchmark emphasizing user-centered metrics such as predictability, oversight effort, and time-to-recovery.
(Tentative; will follow the official IUI 2026 timeline)
Abstract submission (optional): December 10, 2025
Paper submission deadline: December 17, 2025
Notification of acceptance: January 2, 2026
Workshop day: Probably March 23, 2026