English

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

Multiagent Systems 2024-08-15 v2 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2408.02117,
  title  = {Value-Based Rationales Improve Social Experience: A Multiagent Simulation Study},
  author = {Sz-Ting Tzeng and Nirav Ajmeri and Munindar P. Singh},
  journal= {arXiv preprint arXiv:2408.02117},
  year   = {2024}
}

Comments

13 pages, 13 figures, 13 tables (and supplementary material with reproducibility and additional results), accepted at ECAI 2024

R2 v1 2026-06-28T18:03:39.495Z