On the Utility of Accounting for Human Beliefs about AI Intention in Human-AI Collaboration

TL;DR

This paper introduces a model for AI agents to consider human beliefs about AI intentions, improving collaboration effectiveness by adapting to human perceptions and reasoning about AI goals.

Contribution

It presents a novel belief model capturing human interpretations of AI intentions and integrates this into AI strategy design for better collaboration.

Findings

The belief model accurately predicts human perceptions of AI intentions.

AI agents considering human beliefs outperform traditional models in collaboration tasks.

Human-AI collaboration improves significantly with belief-aware AI strategies.

Abstract

To enable effective human-AI collaboration, merely optimizing AI performance without considering human factors is insufficient. Recent research has shown that designing AI agents that take human behavior into account leads to improved performance in human-AI collaboration. However, a limitation of most existing approaches is their assumption that human behavior remains static, regardless of the AI agent's actions. In reality, humans may adjust their actions based on their beliefs about the AI's intentions, specifically, the subtasks they perceive the AI to be attempting to complete based on its behavior. In this paper, we address this limitation by enabling a collaborative AI agent to consider its human partner's beliefs about its intentions, i.e., what the human partner thinks the AI agent is trying to accomplish, and to design its action plan accordingly to facilitate more effective human-AI collaboration. Specifically, we developed a model of human beliefs that captures how humans interpret and reason about their AI partner's intentions. Using this belief model, we created an AI agent that incorporates both human behavior and human beliefs when devising its strategy for interacting with humans. Through extensive real-world human-subject experiments, we demonstrate that our belief model more accurately captures human perceptions of AI intentions. Furthermore, we show that our AI agent, designed to account for human beliefs over its intentions, significantly enhances performance in human-AI collaboration.