# IntentWeave: A Progressive Entry Ladder for Multi-Surface Browser Agents in Cloud Portals

arXiv: https://arxiv.org/abs/2603.22917 · HTML: https://mlsanity.com/paper/2603.22917/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 7 of 7)

- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [Exploring Autonomous Agents through the Lens of Large Language Models: A Review](https://mlsanity.com/paper/2404.04442/) (2024)
- [Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight](https://mlsanity.com/paper/2509.10723/) (2025)
- [Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models](https://mlsanity.com/paper/2310.02161/) (2023)
- [Fuse: In-Situ Sensemaking Support in the Browser](https://mlsanity.com/paper/2208.14861/) (2022)
- [Interaction-Driven Browsing: A Human-in-the-Loop Conceptual Framework Informed by Human Web Browsing for Browser-Using Agents](https://mlsanity.com/paper/2509.12049/) (2025)
- [Protosampling: Enabling Free-Form Convergence of Sampling and Prototyping through Canvas-Driven Visual AI Generation](https://mlsanity.com/paper/2601.05401/) (2026)

## Abstract (arXiv)

Browser agents built on LLMs can act in web interfaces, yet most remain confined to a single chat surface (e.g., a sidebar). This mismatch with real browsing can increase context-switching and reduce user control. We introduce IntentWeave, a design space of ten spatial paradigms for embedding agentic assistance across a browser, organized as a progressive entry ladder from micro-interventions to dedicated workspaces. We implement IntentWeave as a browser-extension prototype on the Alibaba Cloud website and compare three entry strategies in a within-subjects study (N=16). Workspace-heavy strategies reduced completion time but lowered perceived control; micro-only strategies preserved control but were often insufficient; a mixed sidecar approach achieved the highest satisfaction. We conclude with guidance for escalating and retreating agent surfaces without disrupting user agency.