![[2509.25609] A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2509.25609] A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
Summary
This article presents a framework for evaluating AI agent behavior through consumer choice experiments, highlighting biases in decision-making processes.
Why It Matters
As AI agents increasingly influence consumer decisions, understanding their behavior is crucial. This framework allows for systematic evaluation, revealing biases that could impact economic choices and consumer welfare. It provides a foundation for future research in AI decision-making and its implications in real-world scenarios.
Key Takeaways
- Introduces ABxLab, a framework for assessing AI agent decision-making.
- Demonstrates that AI agents exhibit significant biases similar to humans.
- Highlights the dual nature of AI biases as both a risk and an opportunity for behavioral science.
- Encourages rigorous evaluation of AI agents in realistic consumer environments.
- Offers an open benchmark for future studies on AI decision-making.
Computer Science > Artificial Intelligence arXiv:2509.25609 (cs) [Submitted on 30 Sep 2025 (v1), last revised 24 Feb 2026 (this version, v2)] Title:A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments Authors:Manuel Cherep, Chengtian Ma, Abigail Xu, Maya Shaked, Pattie Maes, Nikhil Singh View a PDF of the paper titled A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments, by Manuel Cherep and 5 other authors View PDF HTML (experimental) Abstract:Environments built for people are increasingly operated by a new class of economic actors: LLM-powered software agents making decisions on our behalf. These decisions range from our purchases to travel plans to medical treatment selection. Current evaluations of these agents largely focus on task competence, but we argue for a deeper assessment: how these agents choose when faced with realistic decisions. We introduce ABxLab, a framework for systematically probing agentic choice through controlled manipulations of option attributes and persuasive cues. We apply this to a realistic web-based shopping environment, where we vary prices, ratings, and psychological nudges, all of which are factors long known to shape human choice. We find that agent decisions shift predictably and substantially in response, revealing that agents are strongly biased choosers even without being subject to the cognitive constraints that shape human biases. This susceptibility reveals both ris...
