Orca: Browsing at Scale Through User-Driven and AI-Facilitated Orchestration Across Malleable Webpages

2025-05-28

AI Summary

Current browser tab-stacking paradigms impede cross-page information integration, while fully automated AI browsing systems compromise user agency and contextual understanding. To address this, we propose Orca—the first AI-augmented browser—introducing the novel concept of *malleable web pages*, wherein web content is modeled as dynamic, human-AI co-editable material. Orca implements a browser-level composable workspace integrating interactive AI agents, real-time DOM restructuring, multi-page contextual modeling, and collaborative orchestration interfaces. Empirical evaluation demonstrates that Orca significantly enhances users’ information foraging motivation and perceived control, while improving both flexibility and efficiency in cross-page sensemaking. By unifying human intent with adaptive AI assistance, Orca extends web information processing capabilities along both breadth (multi-page scope) and depth (semantic coherence and actionable insight generation).

Technology Category

• Humans and AI: Intelligent User Interfaces
• Multiagent Systems: Modeling other Agents
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Web-based activities are fundamentally distributed across webpages. However, conventional browsers with stacks of tabs fail to support operating and synthesizing large volumes of information across pages. While recent AI systems enable fully automated web browsing and information synthesis, they often diminish user agency and hinder contextual understanding. Therefore, we explore how AI could instead augment users' interactions with content across webpages and mitigate cognitive and manual efforts. Through literature on information tasks and web browsing challenges, and an iterative design process, we present a rich set of novel interactions with our prototype web browser, Orca. Leveraging AI, Orca supports user-driven exploration, operation, organization, and synthesis of web content at scale. To enable browsing at scale, webpages are treated as malleable materials that humans and AI can collaboratively manipulate and compose into a malleable, dynamic, and browser-level workspace. Our evaluation revealed an increased"appetite"for information foraging, enhanced user control, and more flexibility in sensemaking across a broader information landscape on the web.

Problem

• Supporting large-scale information synthesis across webpages
• Balancing AI automation with user control in browsing
• Enhancing user-driven exploration and organization of web content

Innovation

• AI-augmented user-driven web content exploration
• Malleable webpage manipulation with AI collaboration
• Dynamic browser-level workspace for information synthesis