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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Parmar, Mehul, Silpasuwanchai, Chaklam
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910068267548672
author Parmar, Mehul
Silpasuwanchai, Chaklam
author_facet Parmar, Mehul
Silpasuwanchai, Chaklam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22766
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization
Parmar, Mehul
Silpasuwanchai, Chaklam
Human-Computer Interaction
Artificial Intelligence
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.
title From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2603.22766