The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes

Human-LLM CollaborationAI-Assisted Decision-Making & AutomationAI Ethics, Fairness & AccountabilityRecommender System UXSoftware Engineers & DevelopersUI/UX DesignersAI/ML Researchers & Engineers

Large Language Model (LLM)-powered web GUI agents are increasingly automating everyday online tasks. Despite their popularity, little is known about how users' preferences and values impact agents' reasoning and behavior. In this work, we investigate how both explicit and implicit user preferences, as well as the underlying user values, influence agent decision-making and action trajectories. We built a controlled testbed of 14 common interactive web tasks, spanning shopping, travel, dining, and housing, each replicated from real websites and integrated with a low-fidelity LLM-based recommender system. We injected 12 human preferences and values as personas into four state-of-the-art agents and systematically analyzed their task behaviors. Our results show that preference and value-infused prompts consistently guided agents toward outcomes that reflected these preferences and values. While the absence of user preference or value guidance led agents to exhibit a strong efficiency bias and employ shortest-path strategies, their presence steered agents' behavior trajectories through the greater use of corresponding filters and interactive web features. Despite their influence, dominant interface cues, such as discounts and advertisements, frequently overrode these effects, shortening the agents' action trajectories and inducing rationalizations that masked rather than reflected value-consistent reasoning. The contributions of this paper are twofold: (1) an open-source testbed for studying the influence of values in agent behaviors, and (2) an empirical investigation of how user preferences and values shape web agent behaviors.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/iui/226622/2026

AdRecommended

Learn AI Coding at CodeNow

At a Glance

Paper Snapshot

fact_check
dataset
Source
IUI
calendar_month
Year
2026
emoji_events
Award
No award tagged
group
Authors
10 authors
sell
Subtopics
Human-LLM Collaboration, AI-Assisted Decision-Making & Automation, AI Ethics, Fairness & Accountability, Recommender System UX
work
Professions
Software Engineers & Developers, UI/UX Designers, AI/ML Researchers & Engineers
article
Content Status
Abstract only
hub
Related Papers
10 related papers