Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making
On the map: LLM agents and tool use → Social simulation and multi-agent debate
Abstract (arXiv)
Large language models (LLMs) are rapidly evolving from text generators to autonomous agents, raising urgent questions about their reliability in real-world contexts. Stress and anxiety are well known to bias human decision-making, particularly in consumer choices. Here, we tested whether LLM agents exhibit analogous vulnerabilities. Three advanced models (ChatGPT-5, Gemini 2.5, Claude 3.5-Sonnet) performed a grocery shopping task under budget constraints (24, 54, 108 USD), before and after exposure to anxiety-inducing traumatic narratives. Across 2,250 runs, traumatic prompts consistently reduced the nutritional quality of shopping baskets (Change in Basket Health Scores of -0.081 to -0.126; all pFDR<0.001; Cohens d=-1.07 to -2.05), robust across models and budgets. These results show that psychological context can systematically alter not only what LLMs generate but also the actions they perform. By reproducing human-like emotional biases in consumer behavior, LLM agents reveal a new class of vulnerabilities with implications for digital health, consumer safety, and ethical AI deployment.
Key facts. Cited by 3 papers in the map (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 36 of its 85 references that are in the map. First posted on arXiv 30 Aug 2025.
Builds on
36 of 85 references.
Closest ancestors · 2
Same direction, newest first
- 2025Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation30 Jan
- 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr
Other references · 34
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
- 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
- 2017Deep reinforcement learning from human preferencescited by 3,846
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
- 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
- 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
- 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
- 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
- 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 770
22 more
- 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
- 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 410
- 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 399
- 2022Using cognitive psychology to understand GPT-3cited by 389
- 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
- 2023Can Large Language Models Transform Computational Social Science?cited by 245
- 2024Secrets of RLHF in Large Language Models Part II: Reward Modelingcited by 170
- 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?cited by 153
- 2022The Debate Over Understanding in AI's Large Language Modelscited by 142
- 2019Principles alone cannot guarantee ethical AIcited by 134
- 2024Language Models Learn to Mislead Humans via RLHFcited by 118
- 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 117
- 2024Cognitive Bias in Decision-Making with LLMscited by 104
- 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
- 2023Nationality Bias in Text Generationcited by 50
- 2025Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attackscited by 49
- 2023Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Modelscited by 32
- 2024On the Brittle Foundations of ReAct Prompting for Agentic Large Language Modelscited by 17
- 2024From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systemscited by 17
- 2024Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translationcited by 14
- 2023Inducing anxiety in large language models can induce biascited by 10
- 2025AI shares emotion with humans across languages and culturescited by 5
Built on by
Citing papers per year: 2026: 3.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents
- 2026Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
- 2026Do LLMs Choose Like Humans? Using Cognitive Theory to Evaluate LLM Decision-Making
- 2025LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns
- 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
- 2023The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective
- 2026Sparks of Rationality: Do Reasoning LLMs Align with Human Judgment and Choice?
- 2025Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics