Ream: Unfolding Mutual Awareness in Human-Agent Workspaces

2026-10-07

AI Summary

This study addresses the mutual awareness deficits in human-AI collaboration arising from overly rapid agent actions and users' implicit expression of interests. To mitigate these issues, we propose a shared-document-based collaborative framework for literature review. Through structured artifact design and bidirectional participation trace tracking, the framework renders human-AI activities transparent and traceable, thereby supporting evidence verification, agent guidance, and reflection on research focus. An experimental evaluation with eighteen researchers demonstrates that this approach effectively enhances collaboration transparency, personalized assistance capabilities, and coordination in knowledge work. Ultimately, this work offers a novel paradigm for human-AI collaborative research by systematically bridging perceptual gaps between human users and AI agents.

Abstract

As AI agents work alongside humans in shared workspaces, a mutual awareness challenge arises: agents act at speeds that outpace human monitoring, and users' evolving interests are not always expressed in chat. This challenge is especially pressing in literature review, where both parties retrieve, read, and synthesize a growing body of papers. We present Ream, a literature review workspace that supports mutual awareness through structured artifacts, bidirectional engagement tracking, and localized visualizations. Users can see each party's activity within these documents, and agents can retrieve the same history to guide their work. In studies with eighteen researchers, participants used these traces to inspect evidence, steer agents, communicate through annotations, and reflect on their research focus. Shared histories also helped agents build on earlier work. These findings inform how engagement traces within shared documents can support transparency, personalized assistance, and coordination in human-agent knowledge work.

Problem

• Mutual Awareness
• Human-Agent Collaboration
• Literature Review
• Shared Workspace

Innovation

• Mutual Awareness
• Human-Agent Collaboration
• Engagement Tracking
• Literature Review
• Shared Artifacts