It is found that correctly inferring user preferences is necessary but not sufficient for task success, as execution failures in downstream web interactions remain a significant bottleneck even when agents align with the target preference.
Dong-Chan Shin, Xing Han Lù, Jiaqi Deng et al.· 0 citations
A variant of FocusAgent significantly reduces the success rate of prompt-injection attacks, including banner and pop-up attacks, while maintaining task success performance in attack-free settings, highlighting that targeted LLM-based retrieval is a practical and robust strategy for building web agents that are efficien...
Imene Kerboua, S. Shayegan, Megh Thakkar et al.· arXiv.org· 15 citations
These results show that current agents are still far from professional-level computer use: rather than stumbling on basic GUI control or coding, they lose track of constraints, miss information that arrives mid-task, guess rather than ask the user, and skip verification, struggling most when a task hinges on hidden sta...