Intelligent Reasoning Cues: A Framework and Case Study of the Roles of AI Information in Complex Decisions

2026-01-30

AI Summary

While existing AI-assisted decision-making systems achieve high accuracy, they struggle to effectively support users’ complex reasoning in tasks characterized by high variability and discretionary judgment, and lack a clear understanding of how AI-provided information influences human decision mechanisms. This study proposes an “Intelligent Reasoning Cues” framework that, for the first time, decomposes AI interface information into discrete, analyzable reasoning units. Through contextual interviews, think-aloud protocols, and clinical decision analysis in the domain of sepsis critical care, the research systematically evaluates the impact of eight types of reasoning cues on physician decision-making. It reveals distinct mechanisms through which different cue types operate, identifies their task-specific effects on clinical judgments, and formulates three design principles: prioritizing support for high-variability tasks, dynamically adapting to evolving decision needs, and delivering complementary, deep insights—thereby offering a new paradigm for designing AI decision support systems.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Reasoning under Uncertainty: Sequential Decision Making
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Artificial intelligence (AI)-based decision support systems can be highly accurate yet still fail to support users or improve decisions. Existing theories of AI-assisted decision-making focus on calibrating reliance on AI advice, leaving it unclear how different system designs might influence the reasoning processes underneath. We address this gap by reconsidering AI interfaces as collections of intelligent reasoning cues: discrete pieces of AI information that can individually influence decision-making. We then explore the roles of eight types of reasoning cues in a high-stakes clinical decision (treating patients with sepsis in intensive care). Through contextual inquiries with six teams and a think-aloud study with 25 physicians, we find that reasoning cues have distinct patterns of influence that can directly inform design. Our results also suggest that reasoning cues should prioritize tasks with high variability and discretion, adapt to ensure compatibility with evolving decision needs, and provide complementary, rigorous insights on complex cases.

Problem

• AI-assisted decision-making
• reasoning processes
• decision support systems
• intelligent reasoning cues
• complex decisions

Innovation

• intelligent reasoning cues
• AI-assisted decision-making
• decision support systems
• clinical decision-making
• human-AI interaction