ITO: Real-time Browser Tab Orchestration Through Intent Detection

๐Ÿ“… 2026-08-10
๐Ÿ“ˆ Citations: 0
โœจ Influential: 0
๐Ÿ“„ PDF
๐Ÿค– AI Summary
Modern web browsers lack structured awareness of usersโ€™ multitasking browsing intentions, resulting in inefficient tab management. This work proposes a hybrid proactive approach that dynamically creates, reorganizes, suspends, and resumes task-centric groups called โ€œFlowsโ€ by continuously monitoring browsing context and focus shifts, thereby enabling intention-driven tab organization. The method introduces the first real-time, dynamic, and intention-aware browser tab management mechanism that adapts to evolving user intent while preserving user control. User studies demonstrate that the system aligns closely with usersโ€™ mental models, significantly improving task-switching and navigation efficiency, reducing management overhead, and maintaining a strong sense of user agency.
๐Ÿ“ Abstract
People routinely interleave activities while browsing the web, often simultaneously and with overlapping boundaries. Yet organizational primitives in modern browsers treat every tab uniformly, offering no structural awareness of which items serve which purpose. While task-based organization approaches exist, they typically require users to manually organize or invoke reorganization features, and quickly fall out of sync as user intents evolve. To address this, we present Ito, a mixed-initiative approach that infers user intent in real time and organizes browsing activities into dynamic collections called Flows. Ito continuously reads unfolding user context, determines moment-to-moment focus, and creates, restructures, hibernates, and awakens Flows in real time while preserving user control through a mixed-initiative loop of proposals and corrections. In a controlled lab study (N=12) and a two-week field study (N=11), results suggest that Ito's intent-driven Flows aligned more closely with participants' mental models, facilitated task switching and navigation more effectively, and reduced management burden without loss of perceived control.
Problem

Research questions and friction points this paper is trying to address.

browser tab orchestration
user intent detection
task management
mixed-initiative interaction
real-time organization
Innovation

Methods, ideas, or system contributions that make the work stand out.

intent detection
browser tab orchestration
mixed-initiative interaction
dynamic task organization
real-time context awareness
๐Ÿ”Ž Similar Papers
๐Ÿ’ผ Related Jobs
No related jobs found.
E
Elvin Hu
Graduate School of Media Design, Keio University, Yokohama, Japan
J
Jasmine Sumpter
Graduate School of Media Design, Keio University, Yokohama, Japan
T
Takatoshi Yoshida
Graduate School of Media Design, Keio University, Yokohama, Japan
M
Mauricio Sousa
Graduate School of Media Design, Keio University, Yokohama, Japan
Kouta Minamizawa
Kouta Minamizawa
Professor, Keio University Graduate School of Media Design
HapticsEmbodied MediaVirtual RealityHuman AugmentationHuman-Computer Interaction