Research

Paper

AI LLM February 25, 2026

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

Authors

Otto Nyberg, Fausto Carcassi, Giovanni Cinà

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.

Metadata

arXiv ID: 2602.21889
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-25
Fetched: 2026-02-26 05:00

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21889v1</id>\n    <title>2-Step Agent: A Framework for the Interaction of a Decision Maker with AI Decision Support</title>\n    <updated>2026-02-25T13:11:12Z</updated>\n    <link href='https://arxiv.org/abs/2602.21889v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21889v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-02-25T13:11:12Z</published>\n    <arxiv:comment>17 pages, 17 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Otto Nyberg</name>\n    </author>\n    <author>\n      <name>Fausto Carcassi</name>\n    </author>\n    <author>\n      <name>Giovanni Cinà</name>\n    </author>\n  </entry>"
}