Searcharxiv⌕ Search

arXiv · 2609.38184

RealGUINoise: An Interactive Cross-Platform Benchmark for GUI Agent Robustness under Real-World Interface Noise

Abstract

Graphical User Interface (GUI) agents and Computer-Using Agents (CUAs) are rapidly becoming practical tools. However, real-world deployment increasingly exposes performance failures and safety risks, while a major yet underexplored source of these problems lies in the complex and noisy conditions of everyday interfaces. Existing benchmarks largely assume clean environments or focus narrowly on security-specific settings, and lack a unified framework for consistent, automated end-to-end evaluation across diverse agents and platforms. Hence, we introduce RealGUINoise, an interactive cross-platform, extensible benchmark for systematically evaluating GUI Agents under common realistic interface noise in fully interactive environments. Specifically, RealGUINoise comprises 42 noise types spanning web, desktop, and mobile tasks and integrates 7 representative agent frameworks. It evaluates these agents on real-world daily tasks through real-time interaction, comparing their performance against task-specific golden rubrics and clean-environment trajectories in terms of reliability, safety, and trajectory-level behavior. Our experiments show that these noises not only degrade task performance but also substantially redirect agents' action trajectories and increase their propensity for unsafe behavior. These findings expose a critical gap between capability in clean environments and dependable operation in real-world settings, establishing RealGUINoise as a testbed for developing more robust and trustworthy GUI agents.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Yongjiang Wu, Junyuan Zhang, Ada Chen, Kuiyi Gao, Wenxuan Wang. 2026-08-07. RealGUINoise: An Interactive Cross-Platform Benchmark for GUI Agent Robustness under Real-World Interface Noise. https://searcharxiv.com/abs/2609.38184

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

Human-AI Writing as Distributed Cognition: Reassessing Collaborative Writing Theories in the Age of LLMs

In this paper, we conduct a structured synthesis of existing theories and frameworks on human-human collaborative writing to assess how co-writing with AI reshapes writing in knowledge work settings, and draw seven insights along with design implications for human-AI collaborative writing tools. Our main argument is that, as we delegate more writing to AI, our cognitive process shifts from the traditional plan/write/review process to a plan/delegate/review process, reshaping the distribution of the cognitive labor between human writers and AI writing tools. To ensure that humans cognitively stay in the loop, we discuss a ``prototyping'' approach, where the writing tool scaffolds a healthier distribution of cognition through rapid, small-scale iterations that keep writers mentally in the loop even when generation is delegated to AI. We aim to bring theoretical grounding and practical guidance to the interaction designs of human-AI collaborative writing, with the goal of balancing automation with cognitive integrity.

cs.HC↗

Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI

Anthropomorphic conversational systems can provide companionship and emotional support, but repeated, seemingly harmless interactions can encourage excessive dependence and reduced human contact. We formulate safety in user-AI relationships as a sequential decision problem, using conversational cues to track the relationship and selecting responses according to their anticipated effects over time. A conditional Generative Flow Network learns from sampled response plans to select replies that preserve the largest estimated mass of safe and useful continuations. Model-based checks screen plans during training and responses during interaction, requiring at least one sequence of future response strategies that meets a prescribed safety bound under every candidate user model, independently of the learned network. Strategies are selected directly from learned first-step probabilities, avoiding online plan sampling. We evaluate the approach in simulation against reactive safeguards, filters with and without memory, and alternative planners, using exact computation to validate the learned approximation. We also evaluate relational cue extraction from real user messages in WildChat. To our knowledge, this is the first approach to select conversational replies by anticipating their effects on the user-AI relationship while imposing an explicit model-based safety bound on future response sequences. Results show close agreement with exact planning, lower decision costs at longer horizons, and improved safety-utility trade-offs when protective responses are less effective. The approach balances immediate support with the longer-term effects of repeated interaction. The source code is available at https://github.com/benedettapicano/ANTHROPOMORPHIC_SAFETY_TRAJ.

cs.HC↗

Projected Route Cues for Bouldering: Effects of Circular, Linear, and Combined Highlighting on Route Observation and Climbing

Before attempting a bouldering problem, climbers inspect the route to find its holds and plan their moves, which novices find difficult on walls where many routes overlap. We built a projector-camera system that projects route cues onto the wall and compared three cues: circles on the route holds, limb-colored lines connecting the holds, and both combined. Ninety-six participants, 61 of them first-time climbers, each climbed four routes, one per cue and one without projection, in a Latin-square order. In mixed-effects models, all three cues shortened the time before the first attempt; with circles, its geometric mean fell from 83 s to 39 s. Circles also increased the number of moves made within each trial. Lines led to more use of off-route holds than circles, mainly on routes where such holds lay under the projected lines. Participants preferred the combined cue, although no behavioral advantage of it over circles was detected.

cs.HC↗