Actual Trust in Multiagent Systems

Michael Akintunde; Vahid Yazdanpanah; Asieh Salehi; Corina Cirstea; Mehdi Dastani; Luc Moreau

Actual Trust in Multiagent Systems

Michael Akintunde, Vahid Yazdanpanah, Asieh Salehi, Corina Cirstea, Mehdi Dastani, Luc Moreau

Research output: Contribution to conference types › Abstract › peer-review

32 Downloads (Pure)

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.

Original language	English
Publication status	Published - 6 May 2024

Access to Document

AAMAS_2024_Actual_Trust_In_MultiAgent_SystemsProof, 505 KBLicence: CC BY

Cite this

@conference{b6d7d2761cf04a8c8f67aea03bc64003,

title = "Actual Trust in Multiagent Systems",

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{\textquoteright} 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{\textquoteright}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.",

author = "Michael Akintunde and Vahid Yazdanpanah and Asieh Salehi and Corina Cirstea and Mehdi Dastani and Luc Moreau",

year = "2024",

month = may,

day = "6",

language = "English",

}

TY - CONF

T1 - Actual Trust in Multiagent Systems

AU - Akintunde, Michael

AU - Yazdanpanah, Vahid

AU - Salehi, Asieh

AU - Cirstea, Corina

AU - Dastani, Mehdi

AU - Moreau, Luc

PY - 2024/5/6

Y1 - 2024/5/6

N2 - 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.

AB - 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.

M3 - Abstract

ER -

Actual Trust in Multiagent Systems

Abstract

Access to Document

Fingerprint

Cite this