Explaining and Improving Information Complementarities in Multi-Agent Decision-making

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Ziyang, Wu, Yifan, Hartline, Jason, Hullman, Jessica
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908810274144256
author Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
author_facet Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
contents Multiple agents are increasingly combined to make decisions with the expectation of achieving complementary performance, where the decisions they make together outperform those made individually. However, knowing how to improve the performance of collaborating agents requires knowing what information and strategies each agent employs. With a focus on human-AI pairings, we contribute a decision-theoretic framework for characterizing the value of information. By defining complementary information, our approach identifies opportunities for agents to better exploit available information in AI-assisted decision workflows. We present a novel explanation technique (ILIV-SHAP) that adapts SHAP explanations to highlight human-complementing information. We validate the effectiveness of our framework and ILIV-SHAP through a study of human-AI decision-making, and demonstrate the framework on examples from chest X-ray diagnosis and deepfake detection. We find that presenting ILIV-SHAP with AI predictions leads to reliably greater reductions in error over non-AI assisted decisions more than vanilla SHAP.
format Preprint
id arxiv_https___arxiv_org_abs_2502_06152
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Explaining and Improving Information Complementarities in Multi-Agent Decision-making
Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
Artificial Intelligence
Machine Learning
Multiple agents are increasingly combined to make decisions with the expectation of achieving complementary performance, where the decisions they make together outperform those made individually. However, knowing how to improve the performance of collaborating agents requires knowing what information and strategies each agent employs. With a focus on human-AI pairings, we contribute a decision-theoretic framework for characterizing the value of information. By defining complementary information, our approach identifies opportunities for agents to better exploit available information in AI-assisted decision workflows. We present a novel explanation technique (ILIV-SHAP) that adapts SHAP explanations to highlight human-complementing information. We validate the effectiveness of our framework and ILIV-SHAP through a study of human-AI decision-making, and demonstrate the framework on examples from chest X-ray diagnosis and deepfake detection. We find that presenting ILIV-SHAP with AI predictions leads to reliably greater reductions in error over non-AI assisted decisions more than vanilla SHAP.
title Explaining and Improving Information Complementarities in Multi-Agent Decision-making
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.06152