Personality engineering with AI agents: A new methodology for negotiation research

Abstract:According to canonical negotiation theory, people's success in a negotiation depends on how well they balance competing demands--empathizing and asserting, demonstrating concern for other and concern for self, being soft on the people and hard on the problem. Yet people struggle to manage these tensions, so researchers have lacked the ability to rigorously test the field's prescriptions under controlled conditions. AI agents do not face the same limitations, and their precision, repertoire, consistency, and scalability enable a new class of experiments to contribute to negotiation theory. In this article, we introduce personality engineering--a methodology that precisely parameterizes the personas of AI agents based on established personality frameworks--and propose how this method can be used to study the traits and behaviors of human negotiators. Given its relevance to negotiation theory, we propose the interpersonal circumplex--and its two core dimensions of warmth and dominance--as a foundational coordinate system for the field. This approach offers both a rigorous methodology for testing classic negotiation theories and a practical guide for designing the personas of AI negotiation agents.

Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Social and Information Networks (cs.SI)

arXiv:2605.20554 [cs.AI]

(or arXiv:2605.20554v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.20554 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.