MEDIATE: Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange

Philipp Altmann, Katharina Winter, Michael Kölle, Maximilian Zorn, Claudia Linnhoff-Popien

2025

Abstract

Recent advances in *multi-agent systems* (MAS) have shown that incorporating *peer incentivization* (PI) mechanisms vastly improves cooperation. Especially in social dilemmas, communication between the agents helps to overcome sub-optimal Nash equilibria. However, incentivization tokens need to be carefully selected. Furthermore, real-world applications might yield increased privacy requirements and limited exchange. Therefore, we extend the PI protocol for *mutual acknowledgment token exchange* (MATE) and provide additional analysis on the impact of the chosen tokens. Building upon those insights, we propose *mutually endorsed distributed incentive acknowledgment token exchange* (MEDIATE), an extended PI architecture employing automatic token derivation via decentralized consensus. Empirical results show the stable agreement on appropriate tokens yielding superior performance compared to static tokens and state-of-the-art approaches in different social dilemma environments with various reward distributions.

Paper Citation

in Harvard Style

Altmann P., Winter K., Kölle M., Zorn M. and Linnhoff-Popien C. (2025). MEDIATE: Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 33-44. DOI: 10.5220/0013091900003890

in Bibtex Style

@conference{icaart25,
author={Philipp Altmann and Katharina Winter and Michael Kölle and Maximilian Zorn and Claudia Linnhoff-Popien},
title={MEDIATE: Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2025},
pages={33-44},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013091900003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - MEDIATE: Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange
SN - 978-989-758-737-5
AU - Altmann P.
AU - Winter K.
AU - Kölle M.
AU - Zorn M.
AU - Linnhoff-Popien C.
PY - 2025
SP - 33
EP - 44
DO - 10.5220/0013091900003890
PB - SciTePress