Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model

• URL: http://arxiv.org/abs/2608.26221v1
• Date: Wed, 26 Aug 2026 12:42:36 GMT
• Title: Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model
• Abstract summary: This study explores the sensitivity of generative agents' behavior to prompt modifications and varied persona names of the agents.<n>Using synonymous prompts results in negligible changes to the model's outcomes.<n>Minor variations in prompts, as well as contextual changes, do influence the model's results.
• Score: 0.3093890460224435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As generative AI gains traction, researchers are investigating its potential to serve as proxies for humans. From undergoing cognitive psychology experiments to experiencing an epidemic, generative agents, agents powered by generative AI models, produce realistic human behavior when prompted. This study explores the sensitivity of these generative agents' behavior to prompt modifications and varied persona names of the agents. To assess this sensitivity, we use a generative agent epidemic model, wherein each agent is prompted daily on whether it wants to isolate or commingle with other agents. We found that using synonymous prompts results in negligible changes to the model's outcomes. However, minor variations in prompts, as well as contextual changes, do influence the model's results. Lastly, our data indicates that different persona names assigned to generative agents, specifically those imbued with personas, do not significantly impact epidemic outcomes.

Related papers

• Generating Public Health Responses using Survey-Augmented Large Language Models [0.46906883107634084]
  Epidemiological models often rely on survey data to represent how individuals make health-related decisions.<n>We investigate whether large language models can generate synthetic survey responses that reproduce patterns observed in real populations.
  arXiv  Detail & Related papers  (2026-06-20T01:11:49Z)
• AI Agents as Policymakers in Simulated Epidemics [0.0]
  We develop a generative AI agent to study repetitive policy decisions during an epidemic.<n>We embed the agent, prompted to act as a city mayor, within a simulated SEIR environment.<n>The results illustrate how theory-informed prompting can shape emergent policy behavior in AI agents.
  arXiv  Detail & Related papers  (2026-01-06T03:19:49Z)
• Generative Agent Simulations of 1,000 People [56.82159813294894]
  We present a novel agent architecture that simulates the attitudes and behaviors of 1,052 real individuals. The generative agents replicate participants' responses on the General Social Survey 85% as accurately as participants replicate their own answers. Our architecture reduces accuracy biases across racial and ideological groups compared to agents given demographic descriptions.
  arXiv  Detail & Related papers  (2024-11-15T11:14:34Z)
• Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems [70.84976977950075]
  Real-world multi-agent systems are often dynamic and continuous, where the agents co-evolve and undergo changes in their trajectories and interactions over time. We propose a novel model that captures the continuous interaction among agents using a Graph Neural Network (GNN) as the ODE function. The key innovation of our model is to learn time-dependent representations of treatments and incorporate them into the ODE function, enabling precise predictions of potential outcomes.
  arXiv  Detail & Related papers  (2024-02-29T23:07:07Z)
• Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting [64.80538055623842]
  sociodemographic prompting is a technique that steers the output of prompt-based models towards answers that humans with specific sociodemographic profiles would give. We show that sociodemographic information affects model predictions and can be beneficial for improving zero-shot learning in subjective NLP tasks.
  arXiv  Detail & Related papers  (2023-09-13T15:42:06Z)
• Agent-Based Model: Simulating a Virus Expansion Based on the Acceptance of Containment Measures [65.62256987706128]
  Compartmental epidemiological models categorize individuals based on their disease status. We propose an ABM architecture that combines an adapted SEIRD model with a decision-making model for citizens. We illustrate the designed model by examining the progression of SARS-CoV-2 infections in A Coruna, Spain.
  arXiv  Detail & Related papers  (2023-07-28T08:01:05Z)
• Epidemic Modeling with Generative Agents [1.1342625695057285]
  This study offers a new paradigm of individual-level modeling to address the grand challenge of incorporating human behavior in epidemic models. Using generative artificial intelligence in an agent-based epidemic model, each agent is empowered to make its own reasonings and decisions.
  arXiv  Detail & Related papers  (2023-07-11T02:52:32Z)
• My Actions Speak Louder Than Your Words: When User Behavior Predicts Their Beliefs about Agents' Attributes [5.893351309010412]
  Behavioral science suggests that people sometimes use irrelevant information. We identify an instance of this phenomenon, where users who experience better outcomes in a human-agent interaction systematically rated the agent as having better abilities, being more benevolent, and exhibiting greater integrity in a post hoc assessment than users who experienced worse outcome -- which were the result of their own behavior -- with the same agent. Our analyses suggest the need for augmentation of models so that they account for such biased perceptions as well as mechanisms so that agents can detect and even actively work to correct this and similar biases of users.
  arXiv  Detail & Related papers  (2023-01-21T21:26:32Z)
• What Do You See in this Patient? Behavioral Testing of Clinical NLP Models [69.09570726777817]
  We introduce an extendable testing framework that evaluates the behavior of clinical outcome models regarding changes of the input. We show that model behavior varies drastically even when fine-tuned on the same data and that allegedly best-performing models have not always learned the most medically plausible patterns.
  arXiv  Detail & Related papers  (2021-11-30T15:52:04Z)
• An Agent-Based Model of COVID-19 Diffusion to Plan and Evaluate Intervention Policies [0.09236074230806579]
  The model includes the structural data of Piedmont, an Italian region. The model is generative of complex epidemic dynamics emerging from the consequences of agents' actions and interactions.
  arXiv  Detail & Related papers  (2021-08-19T19:23:17Z)
• Learning Latent Representations to Influence Multi-Agent Interaction [65.44092264843538]
  We propose a reinforcement learning-based framework for learning latent representations of an agent's policy. We show that our approach outperforms the alternatives and learns to influence the other agent.
  arXiv  Detail & Related papers  (2020-11-12T19:04:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.