Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content

arXiv cs.AI Papers
llm-agents prompting social-media-simulation agent-fidelity intuitive-prompting

Summary

This study shows that intuitive prompting improves LLM agents' simulation of individual social media reactions, achieving higher fidelity than analytical methods, even for unfamiliar content.

arXiv:2609.30563v1 Announce Type: new Abstract: Platform policies are increasingly tested on artificial users, making agent fidelity important. Yet convincing fake profiles could also manipulate perceived public opinion before elections. Validation has concentrated on agreement with human behaviour and has paid little attention to whether an agent behaves in line with the profile it was given. The present study profiled eight Serbian participants through a questionnaire, a deep interview, and a written self-presentation, recorded their reactions to sixty-eight social media posts, and asked four language models to predict those reactions under five prompt conditions varying profile content and instruction style. Attitudinal content improved prediction over demographic backstories by a wide margin. Agents matched their stated profiles more closely than participants matched their own survey answers, and consistency proved unrelated to fidelity once profile information was present. Instructing models to respond intuitively and immediately rather than analytically gave the highest fidelity of any condition and cut the compression of individual differences from seven times the human level to three. The advantage held on posts about topics the questionnaire never raised, where that condition reached the highest fidelity of any setup and beat a crowd baseline by a wide margin, which suggests that agents prompted this way could serve as general-purpose simulated users rather than specialists on the topics they were profiled for. Results may bear implications for the development of language models, because intuition-based setups appear better suited to some tasks than reasoning-based ones.
Original Article
View Cached Full Text

Cached at: 09/28/26, 09:39 AM 

# Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content
Source: [https://arxiv.org/abs/2609.30563](https://arxiv.org/abs/2609.30563)
[View PDF](https://arxiv.org/pdf/2609.30563)

> Abstract:Platform policies are increasingly tested on artificial users, making agent fidelity important\. Yet convincing fake profiles could also manipulate perceived public opinion before elections\. Validation has concentrated on agreement with human behaviour and has paid little attention to whether an agent behaves in line with the profile it was given\. The present study profiled eight Serbian participants through a questionnaire, a deep interview, and a written self\-presentation, recorded their reactions to sixty\-eight social media posts, and asked four language models to predict those reactions under five prompt conditions varying profile content and instruction style\. Attitudinal content improved prediction over demographic backstories by a wide margin\. Agents matched their stated profiles more closely than participants matched their own survey answers, and consistency proved unrelated to fidelity once profile information was present\. Instructing models to respond intuitively and immediately rather than analytically gave the highest fidelity of any condition and cut the compression of individual differences from seven times the human level to three\. The advantage held on posts about topics the questionnaire never raised, where that condition reached the highest fidelity of any setup and beat a crowd baseline by a wide margin, which suggests that agents prompted this way could serve as general\-purpose simulated users rather than specialists on the topics they were profiled for\. Results may bear implications for the development of language models, because intuition\-based setups appear better suited to some tasks than reasoning\-based ones\.

## Submission history

From: Ljubisa Bojic \[[view email](https://arxiv.org/show-email/5082ae97/2609.30563)\] **\[v1\]**Thu, 24 Sep 2026 21:14:39 UTC \(714 KB\)

Similar Articles

Interpreting and Steering LLM Agents for Social Simulations

arXiv cs.LG

This paper explores methods to interpret and steer large language model agents in social simulations, comparing prompt-based, SAE-based, and probe-based techniques, and finds that SAE and probe methods often outperform basic prompting for control and interpretability.

Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations

arXiv cs.AI

This University of Zurich paper investigates whether the Illusory Truth Effect replicates across four LLMs (Gemma-3-4b-it, Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, GPT-5-nano) in generative agent-based social media simulations, finding qualitatively distinct repetition effects — including genuine ITE, mere exposure, and no effect — cautioning against assuming uniform bias replication in LLM-based social simulations.