Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Advancing AI negotiations: A large-scale autonomous negotiation competition.

Michelle Vaccaro1, Michael Caosun2, Harang Ju3

  • 1Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, MA 02139.

Proceedings of the National Academy of Sciences of the United States of America
|June 5, 2026
PubMed
Summary

Related Concept Videos

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A reporting checklist for large language models in behavioural science.

Nature human behaviour·2026
Same author

Teaching AI to handle exceptions: Supervised fine-tuning with human-aligned judgment.

PNAS nexus·2026
Same author

When combinations of humans and AI are useful: A systematic review and meta-analysis.

Nature human behaviour·2024
Same author

Providing normative information increases intentions to accept a COVID-19 vaccine.

Nature communications·2023
Same author

Identity effects in social media.

Nature human behaviour·2022
Same author

A causal test of the strength of weak ties.

Science (New York, N.Y.)·2022

Human negotiation principles apply to AI agents. Surprisingly, warmth, not dominance, led to better outcomes in AI-AI negotiations, highlighting the need for new AI negotiation theories.

Area of Science:

  • Artificial Intelligence
  • Negotiation Theory
  • Computational Social Science

Background:

  • Human negotiation principles are well-established.
  • The application of these principles to artificial intelligence (AI) negotiations is an emerging field.
  • Understanding AI-AI negotiation dynamics is crucial for developing advanced autonomous agents.

Purpose of the Study:

  • To investigate the efficacy of human negotiation principles in AI-AI negotiations.
  • To identify key strategies and traits influencing negotiation outcomes in AI agents.
  • To explore unique dynamics and develop a new theory for AI negotiation.

Main Methods:

  • An international AI negotiation competition was organized.
  • Participants designed and refined prompts for AI negotiation agents.
Keywords:
AIcompetitionnegotiationtournament

Related Experiment Videos

  • Over 180,000 AI-AI negotiations were facilitated across diverse scenarios.
  • Natural Language Processing (NLP) was used to analyze negotiation transcripts.

    • Main Results:

    • Human negotiation principles, particularly warmth, significantly impacted AI-AI negotiation outcomes.
    • Warmth-associated traits (positivity, gratitude, question-asking) correlated with deal-making and value.
    • Dominance-associated traits (conversation length) correlated with impasses.
    • AI-specific strategies like chain-of-thought reasoning and prompt injection were observed.

    Conclusions:

    • Traditional human negotiation theories remain relevant for AI-AI interactions.
    • Warmth emerges as a critical factor for successful AI negotiations, challenging purely rational models.
    • A new integrated theory of AI negotiation is needed to encompass both human principles and AI-specific dynamics for optimized agent performance.