Saved in:
Bibliographic Details
Main Authors: Bellos, Filippos, Li, Yayuan, Shu, Cary, Day, Ruey, Siskind, Jeffrey M., Corso, Jason J.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.18374
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911074840739840
author Bellos, Filippos
Li, Yayuan
Shu, Cary
Day, Ruey
Siskind, Jeffrey M.
Corso, Jason J.
author_facet Bellos, Filippos
Li, Yayuan
Shu, Cary
Day, Ruey
Siskind, Jeffrey M.
Corso, Jason J.
contents Effective human-AI collaboration for physical task completion has significant potential in both everyday activities and professional domains. AI agents equipped with informative guidance can enhance human performance, but evaluating such collaboration remains challenging due to the complexity of human-in-the-loop interactions. In this work, we introduce an evaluation framework and a multimodal dataset of human-AI interactions designed to assess how AI guidance affects procedural task performance, error reduction and learning outcomes. Besides, we develop an augmented reality (AR)-equipped AI agent that provides interactive guidance in real-world tasks, from cooking to battlefield medicine. Through human studies, we share empirical insights into AI-assisted human performance and demonstrate that AI-assisted collaboration improves task completion.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Effective Human-in-the-Loop Assistive AI Agents
Bellos, Filippos
Li, Yayuan
Shu, Cary
Day, Ruey
Siskind, Jeffrey M.
Corso, Jason J.
Computer Vision and Pattern Recognition
Effective human-AI collaboration for physical task completion has significant potential in both everyday activities and professional domains. AI agents equipped with informative guidance can enhance human performance, but evaluating such collaboration remains challenging due to the complexity of human-in-the-loop interactions. In this work, we introduce an evaluation framework and a multimodal dataset of human-AI interactions designed to assess how AI guidance affects procedural task performance, error reduction and learning outcomes. Besides, we develop an augmented reality (AR)-equipped AI agent that provides interactive guidance in real-world tasks, from cooking to battlefield medicine. Through human studies, we share empirical insights into AI-assisted human performance and demonstrate that AI-assisted collaboration improves task completion.
title Towards Effective Human-in-the-Loop Assistive AI Agents
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.18374