From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization
arXiv:2603.22766v2 Announce Type: replace-cross 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
The proliferation of AI systems in mediation and negotiation necessitates immediate research into human-AI interaction complexities to ensure effective human agency.
This research provides crucial insights into designing more effective human-AI negotiation interfaces, directly impacting white-collar workflows and the adoption of AI agents.
The understanding of cognitive load in multi-issue human-AI negotiations and the potential for uncertainty-based visualizations to improve outcomes is now enhanced.
- · AI interface designers
- · Businesses adopting AI for complex negotiations
- · Researchers in human-AI interaction
- · AI developers
- · Inefficient AI negotiation platforms
- · Organizations relying on unassisted human-AI negotiation
Improved human performance in multi-issue AI-mediated negotiations.
Accelerated adoption of AI agents for complex tasks due to enhanced human-AI collaboration.
Shift in white-collar job requirements, emphasizing skills in interpreting and leveraging AI-generated insights rather than raw data processing.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI