Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tzeng, Sz-Ting, Ajmeri, Nirav, Singh, Munindar P.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929458907185152
author Tzeng, Sz-Ting
Ajmeri, Nirav
Singh, Munindar P.
author_facet Tzeng, Sz-Ting
Ajmeri, Nirav
Singh, Munindar P.
contents We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exannaagent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02117
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study
Tzeng, Sz-Ting
Ajmeri, Nirav
Singh, Munindar P.
Multiagent Systems
Artificial Intelligence
Machine Learning
We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exannaagent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.
title Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2408.02117