From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization

TL;DR

This paper investigates how increasing the number of issues in human-AI negotiations affects human performance and introduces a Bayesian visualization tool that improves outcomes and efficiency in complex negotiations.

Contribution

It presents a novel uncertainty-based Bayesian visualization to support multi-issue negotiations, enhancing human performance and decision-making in complex scenarios.

Findings

Performance declines with more than three issues without support

The visualization improves negotiation outcomes and efficiency

Supports human control and avoids redistributing value

Abstract

As AI systems increasingly mediate negotiations, understanding how the number of negotiated issues impacts human performance is crucial for maintaining human agency. We designed a human-AI negotiation case study in a realistic property rental scenario, varying the number of negotiated issues; empirical findings show that without support, performance stays stable up to three issues but declines as additional issues increase cognitive load. To address this, we introduce a novel uncertainty-based visualization driven by Bayesian estimation of agreement probability. It shows how the space of mutually acceptable agreements narrows as negotiation progresses, helping users identify promising options. In a within-subjects experiment (N=32), it improved human outcomes and efficiency, preserved human control, and avoided redistributing value. Our findings surface practical limits on the complexity people can manage in human-AI negotiation, advance theory on human performance in complex negotiations, and offer validated design guidance for interactive systems.