Advancing AI Negotiations: A Large-Scale Autonomous Negotiation Competition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Vaccaro, Michelle, Caosun, Michael, Ju, Harang, Aral, Sinan, Curhan, Jared R.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914253987905536
author Vaccaro, Michelle
Caosun, Michael
Ju, Harang
Aral, Sinan
Curhan, Jared R.
author_facet Vaccaro, Michelle
Caosun, Michael
Ju, Harang
Aral, Sinan
Curhan, Jared R.
contents 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 existing theory, including AI-specific technical strategies like chain-of-thought reasoning and prompt injection. When we applied natural language processing (NLP) 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06416
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Advancing AI Negotiations: A Large-Scale Autonomous Negotiation Competition
Vaccaro, Michelle
Caosun, Michael
Ju, Harang
Aral, Sinan
Curhan, Jared R.
Artificial Intelligence
Human-Computer Interaction
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 existing theory, including AI-specific technical strategies like chain-of-thought reasoning and prompt injection. When we applied natural language processing (NLP) 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.
title Advancing AI Negotiations: A Large-Scale Autonomous Negotiation Competition
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2503.06416