Metraipolis › archive › dc_99f2009d935d
Classic AI Scaffolding for LLM Social Agents — arXiv:2609.01167
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01167
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:30:48.741Z
- SHA-256 of the archived text
455d7e8ad0b3ab9dcb7f78c4b23e39bbcda45382299a35b585123d9de8f49344- Stable URL of this page
https://metraipolis.com/documento/dc_99f2009d935d
How to cite
Classic AI Scaffolding for LLM Social Agents — arXiv:2609.01167 — arXiv (en), https://arxiv.org/abs/2609.01167 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99f2009d935d (Metraipolis archive dc_99f2009d935d, sha256 455d7e8ad0b3ab9dcb7f78c4b23e39bbcda45382299a35b585123d9de8f49344)
BibTeX
@misc{dc99f2009d935d,
title = {Classic AI Scaffolding for LLM Social Agents — arXiv:2609.01167},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01167},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99f2009d935d; sha256 455d7e8ad0b3ab9dcb7f78c4b23e39bbcda45382299a35b585123d9de8f49344},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01167. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models can produce locally plausible social turns, but fluent next-turn generation is not enough for social simulation. Human encounters such as restaurant lunches and hotel check-ins are bounded social episodes with roles, scripts, material state, obligations, commitments, timing, and closure conditions. We present EpisodeSim, a hybrid LLM-agent architecture that represents classic-AI structures as natural-language control state interpreted by LLM calls. A World Master maintains shared reality, constructs scenes, adjudicates proposed actions, tracks effects and obligations, and controls closure. Experiments with small qualitative ablations on two held-out settings support a design claim: LLM fluency supplies local texture, but coherent social simulation benefits from persistent classic-AI-style scaffolding that organizes behavior over time. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.01167 — 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 2026-10-17T06:14:52.151Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).