"Zooming In" on Agentic Web Browsers as Assistive Technologies: A Case Study with a Low-Vision Technology Expert
2026-06-23 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors studied Agentic Web Browsers (AWBs), which use advanced language models to browse the internet on behalf of users. They focused on how AWBs could help people with low vision by making web navigation more like a natural conversation. Their case study with a low-vision expert showed that although AWBs still have some limitations, they make browsing smoother and more flexible for visually-impaired users. The authors suggest that AWBs could improve web accessibility and user experience more broadly in the future.
Agentic Web BrowsersLarge Language ModelsAssistive TechnologiesVisually-Impaired AccessibilityWeb NavigationUser ExperienceConversational InterfacesLow-Vision Technology
Authors
Laura Colazzo, Giuseppe Anzillotti
Abstract
Agentic Web Browsers (AWBs), powered by Large Language Models (LLMs), are emerging as autonomous systems capable of navigating the Web on behalf of users. Beyond enhancing productivity, they could also offer significant promise as Assistive Technologies (ATs) for visually-impaired individuals, transforming web interaction into a fluid conversational exchange. In this paper, we present a case study with a low-vision technology expert, examining how AWBs can support visually-impaired users in web navigation. The findings show that, despite the current limitations, the navigation experience is notably fluid and flexible, underscoring the strong potential of AWBs to enhance accessibility and reduce barriers in web interaction, with implications that may extend beyond accessibility to agentic UX more broadly.