Designing Intent Communication for Agent-Human Collaboration

TL;DR

The paper addresses the problem of safely and intuitively communicating agent intentions across diverse tasks and environments. It introduces a three-axis design space—Transparency, Abstraction, and Modality—and anchors it in Situational Awareness concepts to guide what, when, and how to communicate. Across three collaboration scenarios, the authors provide analytical guidelines and design principles for each dimension, demonstrating cross-domain generalization and identifying opportunities where new signaling strategies are needed. The work aims to enable scalable, transferable, and adaptive intent signaling that enhances trust, reduces cognitive load, and improves collaboration between humans and autonomous agents in real-world settings.

Abstract

As autonomous agents, from self-driving cars to virtual assistants, become increasingly present in everyday life, safe and effective collaboration depends on human understanding of agents' intentions. Current intent communication approaches are often rigid, agent-specific, and narrowly scoped, limiting their adaptability across tasks, environments, and user preferences. A key gap remains: existing models of what to communicate are rarely linked to systematic choices of how and when to communicate, preventing the development of generalizable, multi-modal strategies. In this paper, we introduce a multidimensional design space for intent communication structured along three dimensions: Transparency (what is communicated), Abstraction (when), and Modality (how). We apply this design space to three distinct human-agent collaboration scenarios: (a) bystander interaction, (b) cooperative tasks, and (c) shared control, demonstrating its capacity to generate adaptable, scalable, and cross-domain communication strategies. By bridging the gap between intent content and communication implementation, our design space provides a foundation for designing safer, more intuitive, and more transferable agent-human interactions.

Figures (1)

• Figure 1: Illustration of three distinct application scenarios. From top to bottom: (1) Bystander Interaction, (2) Cooperative Task, and (3) Shared Control. Image generated using GPT-5.