Towards Effective Human-in-the-Loop Assistive AI Agents

• URL: http://arxiv.org/abs/2507.18374v1
• Date: Thu, 24 Jul 2025 12:50:46 GMT
• Title: Towards Effective Human-in-the-Loop Assistive AI Agents
• Authors: Filippos Bellos, Yayuan Li, Cary Shu, Ruey Day, Jeffrey M. Siskind, Jason J. Corso,
• Abstract summary: We introduce an evaluation framework and a dataset of human-AI interactions to assess how AI guidance affects procedural task performance.<n>We also develop an AR-equipped AI agent that provides interactive guidance in real-world tasks, from cooking to battlefield medicine.
• Score: 15.11527529177358
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Operationalizing AI for Good: Spotlight on Deployment and Integration of AI Models in Humanitarian Work [52.96150571365764]
  We share details about the close collaboration with a humanitarian-to-humanitarian (H2H) organization.<n>We discuss how to deploy the AI model in a resource-constrained environment, and how to maintain it for continuous performance updates.
  arXiv  Detail & Related papers  (2025-07-21T17:30:38Z)
• A Task-Driven Human-AI Collaboration: When to Automate, When to Collaborate, When to Challenge [16.734679201317896]
  We show how proper human-AI integration maintains meaningful agency while improving performance.<n>This framework lays the foundation for practically effective and morally sound human-AI collaboration.
  arXiv  Detail & Related papers  (2025-05-23T23:19:15Z)
• Unexploited Information Value in Human-AI Collaboration [23.353778024330165]
  How to improve performance of a human-AI team is often not clear without knowing what particular information and strategies each agent employs.<n>We propose a model based in statistical decision theory to analyze human-AI collaboration.
  arXiv  Detail & Related papers  (2024-11-03T01:34:45Z)
• Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task [56.92961847155029]
  Theory of Mind (ToM) significantly impacts human collaboration and communication as a crucial capability to understand others. Mutual Theory of Mind (MToM) arises when AI agents with ToM capability collaborate with humans. We find that the agent's ToM capability does not significantly impact team performance but enhances human understanding of the agent.
  arXiv  Detail & Related papers  (2024-09-13T13:19:48Z)
• Human Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information [7.475784495279183]
  One promising approach to leverage existing complementary capabilities is allowing humans to delegate individual instances of decision tasks to AI.<n>We conduct a behavioral study to explore the effects of providing contextual information to support this delegation decision.<n>Our findings reveal that access to contextual information significantly improves human-AI team performance in delegation settings.
  arXiv  Detail & Related papers  (2024-01-09T18:59:47Z)
• Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback [42.19685958922537]
  We argue that human-AI collaboration should be interactive, with humans monitoring the work of AI agents and providing feedback that the agent can understand and utilize. In this work, we explore these directions using the challenging task defined by the IGLU competition, an interactive grounded language understanding task in a MineCraft-like world.
  arXiv  Detail & Related papers  (2023-04-21T05:37:59Z)
• Human-AI Collaboration: The Effect of AI Delegation on Human Task Performance and Task Satisfaction [0.0]
  We show that task performance and task satisfaction improve through AI delegation. We identify humans' increased levels of self-efficacy as the underlying mechanism for these improvements. Our findings provide initial evidence that allowing AI models to take over more management responsibilities can be an effective form of human-AI collaboration.
  arXiv  Detail & Related papers  (2023-03-16T11:02:46Z)
• BO-Muse: A human expert and AI teaming framework for accelerated experimental design [58.61002520273518]
  Our algorithm lets the human expert take the lead in the experimental process. We show that our algorithm converges sub-linearly, at a rate faster than the AI or human alone.
  arXiv  Detail & Related papers  (2023-03-03T02:56:05Z)
• Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment [52.07473934146584]
  We guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process. Our system is highly parallelizable, making it possible for a human to train large-scale reinforcement learning applications. It shows reinforcement learning performance can successfully adjust in sync with the human desired difficulty level.
  arXiv  Detail & Related papers  (2022-08-04T23:53:51Z)
• Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration [116.28433607265573]
  We introduce Watch-And-Help (WAH), a challenge for testing social intelligence in AI agents. In WAH, an AI agent needs to help a human-like agent perform a complex household task efficiently. We build VirtualHome-Social, a multi-agent household environment, and provide a benchmark including both planning and learning based baselines.
  arXiv  Detail & Related papers  (2020-10-19T21:48:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.