Designing Intent Communication for Agent-Human Collaboration

TL;DR

This paper introduces a multidimensional design space for agent intent communication, enabling adaptable, scalable, and cross-domain strategies to improve human-agent collaboration safety and intuitiveness.

Contribution

It proposes a systematic framework linking what, when, and how to communicate agent intentions across diverse scenarios.

Findings

The design space effectively generates adaptable communication strategies.

Application to three scenarios demonstrates versatility.

Framework enhances safety and intuitiveness in human-agent interactions.

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.