Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mehul Parmar, Chaklam Silpasuwanchai

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.

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

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.
Paper Structure (100 sections, 19 equations, 11 figures, 3 tables)

This paper contains 100 sections, 19 equations, 11 figures, 3 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Cognitive Limits and Dimensionality in Multi-Issue Negotiations
  4. Human-AI Negotiation Agents and Behavioral Asymmetries
  5. Visualization and Decision Support for Uncertainty in Complex Human-AI Interactions
  6. METHODOLOGY
  7. Design of Negotiation Tasks
  8. Scenario Selection and Ecological Validity
  9. Issue Design and Structural Choices
  10. Anti-triviality and hidden-information safeguards
  11. Dependent Variables
  12. Proxies for Performance
  13. Proxies for Friction
  14. AI Agent Configuration
  15. Example Prompts
  16. ...and 85 more sections

Figures (11)

  • Figure 1: Heatmap of Pareto‑optimal placements: 2‑D distribution of joint‑optimum points across issues, showing dispersed optima that encourage exploratory search rather than midpoint convergence.
  • Figure 2: Sample conversation between a human participant and the AI agent, in the Decision Support condition, showing the visualization interface in action. Green bands of the Negotiation Horizon Grid indicate ZOPA, whereas the Global Convergence Panel shows overall convergence and favorability.
  • Figure 3: Panel (a) shows an early-stage negotiation where the wide colored zone indicates high uncertainty about likely agreement ranges; panel (b) shows a mid-stage negotiation with reduced uncertainty; panel (c) shows a potential late-stage convergence where the colored zone is much narrower (low uncertainty) and the ZOPA is increasingly favorable to the human participant.
  • Figure 4: Overview of the negotiation chatbot system architecture.
  • Figure 5: An overview of the Experimental Procedure.
  • ...and 6 more figures