Metraipolis › archive › dc_7282fbbc1dc5
EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models — arXiv:2610.02744
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02744
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:51:34.087Z
- SHA-256 of the archived text
dcc50f1924dc1c07ba6be0e9c4b18f01ad5d60dcbb924ab4b3c7b54752290c72- Stable URL of this page
https://metraipolis.com/documento/dc_7282fbbc1dc5
How to cite
EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models — arXiv:2610.02744 — arXiv, https://arxiv.org/abs/2610.02744 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7282fbbc1dc5 (Metraipolis archive dc_7282fbbc1dc5, sha256 dcc50f1924dc1c07ba6be0e9c4b18f01ad5d60dcbb924ab4b3c7b54752290c72)
BibTeX
@misc{dc7282fbbc1dc5,
title = {EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models — arXiv:2610.02744},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02744},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7282fbbc1dc5; sha256 dcc50f1924dc1c07ba6be0e9c4b18f01ad5d60dcbb924ab4b3c7b54752290c72},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02744. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Epidemic intervention policies are textual artefacts that human decision-makers interpret, justify, and revise through natural language, making large language models a natural candidate for epidemic policy reasoning. A naive LLM, however, lacks the epidemic dynamics needed to project intervention consequences, the quantitative surveillance signals required to assess severity, and the institutional constraints that define admissible actions. We present EpiWorld, a closed-loop framework that grounds an LLM policy actor in a learned action-conditioned epidemiological world model and a tiered skill library of public-health protocols, surveillance tools, and adaptive lessons accumulated through after-action analysis. Given a candidate intervention, the world model predicts regional epidemic evolution and enables fast counterfactual rollouts that provide feedback for policy selection and refinement. Outcomes of simulated futures are distilled into reusable lessons while protocol constraints remain fixed, allowing the decision process to improve without sacrificing interpretability or controllability. We evaluate both the world model and the end-to-end framework on retrospective COVID-19 and Influenza datasets: the world model achieves the best out-of-distribution Peak-MAE among all forecasting baselines, and the closed-loop framework reduces cumulative hospitalisation by up to 59% across datasets and by an average of ~16% across six LLM backbones, outperforming reinforcement-learning and optimal-control policy baselines. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.02744 — 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 2026-10-05T22:46:10.547Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).