Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents

June 12, 2026 Β· Grace Period Β· πŸ› ICML 2026 WORKSHOP

⏳ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Seoyoung Choi, Minseok Ko, Hyunseok Lee, Kunwoong Kim, Woomin Song, Chanseok Jeon, Jinwoo Shin arXiv ID 2606.14106 Category cs.MA: Multiagent Systems Cross-listed cs.CV Citations 0 Venue ICML 2026 WORKSHOP
Abstract
Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, recent work has introduced experiential memory, where agents retrieve prior trajectories to guide decision-making in similar states. More recent approaches further extend this idea to visual memory by storing and retrieving screenshots from past interactions, providing agents with richer contextual information than text-only memories. However, the effect of visual memory in GUI agents remains insufficiently understood: it is unclear which failures visual memory mitigates, or which failures it exacerbates. To systematically analyze the effect of visual memory, we introduce a taxonomy of four GUI agent failures (i.e., cognitive failure, visual state misunderstanding, hidden operation blindness, and grounding error) that map to distinct stages of the perception-reasoning-action pipeline. We find that prepending full-image memory has a divergent effect on the failure distribution: it reduces state-level failures but worsens action-level ones, and increases hidden operation blindness and grounding error. Motivated by this finding, we propose Action-Grounded Visual Memory (AGMem), an action-grounded memory framework for GUI agents. The core idea of AGMem is to store image crops that capture the local GUI region closely related to a successful action or a recovery, rather than storing full screenshots. Experiments on OSWorld show that AGMem improves task success rates by 33.3 % over full-image memory. These results demonstrate that AGMem is an effective representation for visual memory in GUI agents.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Multiagent Systems