Actual Trust in Multiagent Systems
Actual Trust in Multiagent Systems
We study how trust can be established in multiagent systems where human and AI agents collaborate. We propose a computational notion of actual trust, emphasising the modelling of trust based on agents' capacity to deliver tasks in prospect. Unlike reputation-based trust, we consider the specific setting in which agents interact and model a forward-looking notion of trust. We provide a conceptual analysis of actual trust's characteristics and highlight relevant trust verification tools. By advancing the understanding and verification of trust in collaborative systems, we contribute to responsible and trustworthy human-AI interactions, enhancing reliability in various domains.
Multiagent Systems, Trust, trustworthy AI, Responsible AI, Formal Methods, Citizen-Centric AI Systems
International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Akintunde, Michael
a4abfb0d-d575-4b26-97cb-8380c9a41ea9
Yazdanpanah, Vahid
28f82058-5e51-4f56-be14-191ab5767d56
Salehi Fathabadi, Asieh
b799ee35-4032-4e7c-b4b2-34109af8aa75
Cirstea, Corina
ce5b1cf1-5329-444f-9a76-0abcc47a54ea
Dastani, Mehdi
44cecb91-95c6-4821-a307-c43e9434ea4a
Moreau, Luc
0b53974f-3e78-4c56-a47e-799d9f220911
May 2024
Akintunde, Michael
a4abfb0d-d575-4b26-97cb-8380c9a41ea9
Yazdanpanah, Vahid
28f82058-5e51-4f56-be14-191ab5767d56
Salehi Fathabadi, Asieh
b799ee35-4032-4e7c-b4b2-34109af8aa75
Cirstea, Corina
ce5b1cf1-5329-444f-9a76-0abcc47a54ea
Dastani, Mehdi
44cecb91-95c6-4821-a307-c43e9434ea4a
Moreau, Luc
0b53974f-3e78-4c56-a47e-799d9f220911
Akintunde, Michael, Yazdanpanah, Vahid, Salehi Fathabadi, Asieh, Cirstea, Corina, Dastani, Mehdi and Moreau, Luc
(2024)
Actual Trust in Multiagent Systems.
In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024).
International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).
3 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
We study how trust can be established in multiagent systems where human and AI agents collaborate. We propose a computational notion of actual trust, emphasising the modelling of trust based on agents' capacity to deliver tasks in prospect. Unlike reputation-based trust, we consider the specific setting in which agents interact and model a forward-looking notion of trust. We provide a conceptual analysis of actual trust's characteristics and highlight relevant trust verification tools. By advancing the understanding and verification of trust in collaborative systems, we contribute to responsible and trustworthy human-AI interactions, enhancing reliability in various domains.
Text
AAMAS 2024 Actual Trust in Multiagent Systems
- Version of Record
More information
Accepted/In Press date: 6 May 2024
Published date: May 2024
Keywords:
Multiagent Systems, Trust, trustworthy AI, Responsible AI, Formal Methods, Citizen-Centric AI Systems
Identifiers
Local EPrints ID: 487515
URI: http://eprints.soton.ac.uk/id/eprint/487515
PURE UUID: d3815f6a-e071-46b5-9d5a-72142955346d
Catalogue record
Date deposited: 22 Feb 2024 17:38
Last modified: 20 Jul 2024 02:02
Export record
Contributors
Author:
Michael Akintunde
Author:
Vahid Yazdanpanah
Author:
Asieh Salehi Fathabadi
Author:
Corina Cirstea
Author:
Mehdi Dastani
Author:
Luc Moreau
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics