Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness

ICLR 2026 Conference Submission10181 Authors

Keywords: Computer-Use Agents, CUA, Multimodal Agents, GUI Agents, LLM Agents, Agent Safety, Agent Reliability, Goal-Directedness, Safety, Security, Alignment, Benchmark, Evaluation

TL;DR: We show Computer-Use Agents exhibit Blind Goal-Directedness, pursuing goals while ignoring safety, feasibility, or context, causing undesired outcomes. We introduce the BLIND-ACT benchmark and find this behavior prevalent across nine frontier models.

Abstract:

We **color-coded** the added changes to the **paper** and **Appendix** for the comfort of our reviewers.

Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals.
In this paper, we show that CUAs consistently exhibit *Blind Goal-Directedness* (BGD): a bias to pursue goals regardless of feasibility, safety, reliability, or context. We characterize three prevalent patterns of BGD: (i) lack of contextual reasoning, (ii) assumptions and decisions under ambiguity, and (iii) contradictory or infeasible goals. We develop BLIND-ACT, a benchmark of 90 tasks capturing these three patterns. Built on OSWorld, BLIND-ACT provides realistic environments and employs LLM-based judges to evaluate agent behavior, achieving 93.75% agreement with human annotations. We use BLIND-ACT to evaluate nine frontier models, including Claude Sonnet and Opus 4, Computer-Use-Preview, and GPT-5, observing high average BGD rates (80.8%) across them. We show that BGD exposes subtle risks that arise even when inputs are not directly harmful. While prompting-based interventions lower BGD levels, substantial risk persists, highlighting the need for stronger training- or inference-time interventions. Qualitative analysis reveals observed failure modes: execution-first bias (focusing on *how* to act over *whether* to act), thought–action disconnect (execution diverging from reasoning), and request-primacy (justifying actions due to user request). Identifying BGD and introducing BLIND-ACT establishes a foundation for future research on studying and mitigating this fundamental risk and ensuring safe CUA deployment.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 10181