From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization
This addresses the challenge of maintaining human agency in AI-mediated negotiations, offering incremental design guidance for interactive systems.
The study tackled the problem of cognitive overload in human-AI negotiations with multiple issues, finding that performance declines beyond three issues without support. It introduced a Bayesian visualization that improved human outcomes and efficiency in experiments with 32 participants.
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.