2-Step Agent: A Framework for the Interaction of a Decision Maker with AI Decision Support

2026-02-25

AI Summary

This study addresses the limited understanding of adverse effects arising from human–AI interaction in AI-assisted decision-making. The authors propose a “two-stage agent” framework that, for the first time, models—through Bayesian causal inference—how AI predictions update a rational decision-maker’s beliefs and subsequently influence downstream decisions and outcomes. The framework demonstrates that even a single erroneous prior belief can cause AI assistance to degrade decision quality relative to unassisted scenarios. Simulation experiments validate this mechanism and further highlight the critical roles of model transparency and user training in enhancing the effectiveness of AI assistance.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Reasoning under Uncertainty: Sequential Decision Making
• Multiagent Systems: Adversarial Agents

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: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Across a growing number of fields, human decision making is supported by predictions from AI models. However, we still lack a deep understanding of the effects of adoption of these technologies. In this paper, we introduce a general computational framework, the 2-Step Agent, which models the effects of AI-assisted decision making. Our framework uses Bayesian methods for causal inference to model 1) how a prediction on a new observation affects the beliefs of a rational Bayesian agent, and 2) how this change in beliefs affects the downstream decision and subsequent outcome. Using this framework, we show by simulations how a single misaligned prior belief can be sufficient for decision support to result in worse downstream outcomes compared to no decision support. Our results reveal several potential pitfalls of AI-driven decision support and highlight the need for thorough model documentation and proper user training.

Problem

• AI decision support
• human decision making
• belief updating
• downstream outcomes
• causal inference

Innovation

• 2-Step Agent
• Bayesian causal inference
• AI-assisted decision making
• belief updating
• decision support systems