Advancing AI negotiations: A large-scale autonomous negotiation competition.
Clinical Snapshot
PICO Framework
| P — Population | AI negotiation agents designed by competition participants |
| I — Intervention | Various prompt designs and negotiation strategies for AI agents |
| C — Comparator | Different AI agent configurations and negotiation approaches |
| O — Outcomes | Negotiation success rates, value creation/claiming, deal completion, and performance metrics |
Bottom Line
This large-scale computational study examined AI negotiation dynamics through 180,000+ automated negotiations, finding that traditional human negotiation principles like warmth and relationship-building remain important even in AI-AI interactions. While methodologically robust with impressive scale, the research has limited direct clinical applications. The findings may inform future development of AI systems used in healthcare communication or patient interaction, but current relevance to clinical practice is minimal. Healthcare professionals should note this represents foundational research in AI behaviour rather than immediately applicable clinical evidence. The study's primary value lies in advancing understanding of AI system design rather than informing patient care decisions.
Key Findings
P Value: Not reported
Effect Size: Not quantified in abstract
Primary Outcome: AI negotiation success and value creation/claiming
Nnt Or Sensitivity: Warmth consistently associated with superior outcomes across all metrics
Confidence Interval: Not reported
Clinical Application
Not applicable to routine clinical practice No direct relevance to Australian healthcare delivery, PBS, or TGA considerations Limited direct clinical applicability
Abstract
We conducted an international AI negotiation competition in which participants designed and refined prompts for AI negotiation agents. We then facilitated over 180,000 negotiations between these agents across multiple scenarios with diverse characteristics and objectives. Our findings revealed that principles from human negotiation theory remain crucial even in AI-AI contexts. Surprisingly, warmth-a traditionally human relationship-building trait-was consistently associated with superior outcomes across all key performance metrics. Dominant agents, meanwhile, were especially effective at claiming value. Our analysis also revealed unique dynamics in AI-AI negotiations not fully explained by negotiation theory, including AI-specific technical strategies like chain-of-thought reasoning and prompt injection. When we applied natural language processing methods to the full transcripts of all negotiations, we found positivity, gratitude, and question-asking (associated with warmth) were strongly associated with reaching deals as well as objective and subjective value, whereas conversation lengths (associated with dominance) were strongly associated with impasses. The results suggest the need to establish a new theory of AI negotiation, which integrates classic negotiation theory with AI-specific negotiation theories to better understand autonomous negotiations and optimize agent performance.
References
- 1.Vaccaro, M., Caosun, M., Ju, H., Aral, S., & Curhan, J. R. (2026). Advancing AI negotiations: A large-scale autonomous negotiation competition. Proceedings of the National Academy of Sciences of the United States of America. https://doi.org/10.1073/pnas.2521774123
Related Research
Journal of medical Internet research
Advancing Human-Centered AI in Clinical Decision Support: Sociocognitive Human-in-the-Loop Study in HIV Care
2 Aug 2026
Neurological research
Federated deep learning model for epilepsy seizure detection using electroencephalogram (EEG) signal
2 Aug 2026
Neural networks : the official journal of the International Neural Network Society
MFBD: Model-free backdoor defense based on vision-language pre-trained models
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service