Metraipolis › archive › dc_841a06ea4436
Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content — arXiv:2609.30563
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30563
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:37:46.074Z
- SHA-256 of the archived text
386431b2cfe7ddf8b5f1e5c4d784f157a6473e1047cfb6c8e6c9c8fb36c2ffa0- Stable URL of this page
https://metraipolis.com/documento/dc_841a06ea4436
How to cite
Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content — arXiv:2609.30563 — arXiv (en), https://arxiv.org/abs/2609.30563 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_841a06ea4436 (Metraipolis archive dc_841a06ea4436, sha256 386431b2cfe7ddf8b5f1e5c4d784f157a6473e1047cfb6c8e6c9c8fb36c2ffa0)
BibTeX
@misc{dc841a06ea4436,
title = {Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content — arXiv:2609.30563},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30563},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_841a06ea4436; sha256 386431b2cfe7ddf8b5f1e5c4d784f157a6473e1047cfb6c8e6c9c8fb36c2ffa0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30563. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.MA). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA); Social and Information Networks (cs.SI). Pagina del lavoro: https://arxiv.org/abs/2609.30563 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:11:54.453Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).