Advancing AI negotiations: A large-scale autonomous negotiation competition
Top Cited Papers
Open Access
- 5 June 2026
- journal article
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 123 (23)
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.Keywords
All Related Versions
This publication has 66 references indexed in Scilit:
- Negotiating with LLMs: Prompt Hacks, Skill Gaps, and Reasoning Deficits2025
- Learning about the opponent in automated bilateral negotiation: a comprehensive survey of opponent modeling techniquesAutonomous Agents and Multi-Agent Systems, 2015
- Automated negotiation for e-commerce decision making: A goal deliberated agent architecture for multi-strategy selectionDecision Support Systems, 2015
- Negotiation among autonomous computational agents: principles, analysis and challengesArtificial Intelligence Review, 2008
- Choosing Bargaining Partners—An Experimental Study on the Impact of Information About Income, Status and GenderExperimental Economics, 2005
- Assessing and evaluating: Differentiating perspectivesPerformance Improvement Journal, 2002
- Negotiator cognition and rationality: A behavioral decision theory perspectiveOrganizational Behavior and Human Decision Processes, 1992
- Social perception in negotiationOrganizational Behavior and Human Decision Processes, 1990
- Renegotiation in repeated gamesGames and Economic Behavior, 1989
- Research reports. Compromise and logroll: Comparing the efficiency of two bargaining processesSystems Research and Behavioral Science, 1970