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.

Welcome & Opening

A short kickoff to set the stage for a community-driven, cross-industry discussion on trust, usability, and dependable agentic systems.

Featured Opening Talk

A forward-looking perspective on human-centered trust, reliability, and interaction patterns in agentic UIs.

Invited Talks Session

A curated set of high-impact talks exploring diverse facets of trustworthy CUAs, including: Human–AI collaboration and UX patterns, Trust, transparency, and oversight, Safety, diagnostics, and evaluation, Real-world deployment lessons from industry

Research Session

Selected research presentations and emerging findings
 

Interactive Hands-On Segment

An experiential session exploring design patterns, oversight workflows, and recovery UX for agentic systems.

Featured Midday Keynotes

A deep dive on frontier challenges and opportunities in building reliable, human-centered CUAs—spanning evaluation, governance, and real-world constraints.
 

Panel Discussion

A multi-perspective conversation bridging research and practice in trustworthy agentic systems.

Lightning Talks: Benchmarks, Evaluation & Shared Tasks

Fast-paced spotlights on replicability, benchmark design, and community-driven evaluation efforts.

Collaborative Roadmapping Session

Community brainstorming toward the TRUST-CUA checklist and future shared tasks (e.g., CUBench-IUI).