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

A study of eight Serbian participants found that instructing large language models to respond intuitively and immediately produced the highest fidelity of any of five prompt conditions when predicting the participants' reactions to 68 social media posts, according to arXiv paper 2609.30563v1. The intuitive condition cut the compression of individual differences from seven times the human level to three, and it held on posts about topics the questionnaire never raised, beating a crowd baseline by a wide margin. Attitudinal content improved prediction over demographic backstories by a wide margin, and agents matched their stated profiles more closely than participants matched their own survey answers.

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.