TRUST-CUA: Trustworthy Computer-Using Generalist Agents for Intelligent User Interfaces

Paphos, Cyprus

March 23-26, 2026

Welcome

TRUST-CUA @ IUI 2026 brings together the IUI and AI-agent communities to explore how we can build predictable, steerable, and most importantly, trustworthy computer-using agents (CUAs). These agents operate across GUIs, browsers, APIs, and CLIs, and increasingly act as multi-modal collaborators that assist users in completing complex digital tasks.

Workshop Focus

Modern computer-using agents are evolving into generalist, multi-agent systems capable of reasoning across diverse tools and interfaces. They hold tremendous promise for improving productivity, creativity, and automation. However, they also introduce new challenges for reliability, transparency, and user oversight, and despite this potential, real-world business adoption remains limited.

Developing and validating such systems is often slow and costly, especially when safety and compliance are at stake. Even after deployment, ensuring reliability and trustworthiness is difficult: agents can make silent mistakes, repeat past errors, or drift from intended behavior without clear user visibility.

TRUST-CUA @ IUI 2026 addresses these challenges by exploring how to design CUAs that are predictable, auditable, and user-trustable. The workshop focuses on interface and UX paradigms that foster trust, explainability, human-in-the-loop (HITL), and control, as well as evaluation and governance frameworks that ensure accountability in both enterprise and public settings.

By connecting AI, UX, and human-centered design, TRUST-CUA aims to define a roadmap toward reliable, transparent, and production-ready generalist agents that operate safely and effectively across domains.

Topics

Topics include (but are 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

Call for Papers

Important Dates

Abstract Submission

December 10, 2025

Paper Submission Deadline

December 17, 2025

Paper Notification

Jan 2, 2026

Tentative Agenda

09:00 – 09:15 Gathering & Coffee
09:15 – 09:30 Introduction & Opening Remarks (Organizers)
09:30 – 10:00 Keynote I: Human-Centered Trust in Agentic UIs
10:00 – 10:50 Invited Talks
10:50 – 11:10 Coffee Break
11:10 – 11:50 Papers
11:50 – 12:30 Hands-on Tutorial: Oversight & Recovery UX for CUAs
12:30 – 13:30 Lunch Break
13:30 – 14:30 Keynote II: TBD
14:30 – 15:00 Panel Discussion: Bridging Research and Practice in Trustworthy Agentic Systems
15:00 – 15:20 Coffee Break
15:20 – 16:00 Lightning Session: Benchmarks & Shared Tasks for Trustworthy CUAs
16:00 – 16:40 Brainstorm & Conclusions: Toward the TRUST-CUA Checklist & CUBench-IUI
16:40 – 17:00 Closing Remarks