mlsanityData to 7 Oct 2026

LLM Consumer Behavior Theory: Foundations of a Novel Research Field

arXiv 2606.18005 ↗First posted 16 Jun 2026cs.AI econ.GN q-fin.ECcited by 0

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Large language models (LLMs) are increasingly deployed as autonomous agents that make consumption decisions on behalf of users. This shift raises fundamental questions for consumer theory, which has traditionally modeled humans as the primary decision-makers. In this paper, we introduce LLM Consumer Behavior Theory, a new field of study concerned with analyzing consumer behavior in agentic markets. Drawing on classical and behavioral economics alongside recent advances in Natural Language Processing, we formalize how human preferences are reflected and acted upon by LLM-based agents, and how agent-level decisions aggregate into market demand. We unify previously fragmented literature on LLM decision-making, human behavior simulation, and preference elicitation under a common economic lens, highlighting where assumptions, such as rationality and heterogeneity, may fail in agentic markets. Rather than providing empirical validation, this paper outlines the scope of LLM consumer behavior and identifies open research questions related to alignment, preference representation, and market dynamics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 25 of its 48 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

25 of 48 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments30 Sep
  2. 2025The Basic B*** Effect: The Use of LLM-based Agents Reduces the Distinctiveness and Diversity of People's Choices3 Sep
  3. 2025LLM Agents Are Hypersensitive to Nudges16 May
  4. 2025Can Generative AI agents behave like humans? Evidence from laboratory market experiments12 May
  5. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities16 Oct

Other references · 20

  1. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  2. 2021Ethical and social risks of harm from Language Modelscited by 957
  3. 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 137
  4. 2024A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'cited by 114
  5. 2022Capturing Failures of Large Language Models via Human Cognitive Biasescited by 97
  6. 2023Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysiscited by 91
  7. 2024Large Language Models Assume People are More Rational than We Really arecited by 49
  8. 2024Evaluating Large Language Models as Generative User Simulators for Conversational Recommendationcited by 45
  9. 2024LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theorycited by 44
  10. 2024Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Contextcited by 41
  11. 2025Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profilescited by 38
  12. 2024Anchoring Bias in Large Language Models: An Experimental Studycited by 37
8 more
  1. 2025LoRe: Personalizing LLMs via Low-Rank Reward Modelingcited by 34
  2. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 15
  3. 2025Evaluating and Aligning Human Economic Risk Preferences in LLMscited by 7
  4. 2026Behavioral Economics of AI: LLM Biases and Correctionscited by 7
  5. 2024One world, one opinion? The superstar effect in LLM responsescited by 5
  6. 2025FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Datacited by 5
  7. 2025Are Economists Always More Introverted? Analyzing Consistency in Persona-Assigned LLMscited by 3
  8. 2026Would a Large Language Model Pay Extra for a View? Inferring Willingness to Pay from Subjective Choicescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Competitive Market Behavior of LLMs
  2. 2026Do LLMs Choose Like Humans? Using Cognitive Theory to Evaluate LLM Decision-Making
  3. 2024GLEE: A Unified Framework and Benchmark for Language-based Economic Environments
  4. 2024Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models
  5. 2025Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
  6. 2024STEER: Assessing the Economic Rationality of Large Language Models
  7. 2025Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making
  8. 2024Can LLMs Replace Economic Choice Prediction Labs? The Case of Language-based Persuasion Games