arXiv：cs.CL· Zeeshan Memon, Yiqi Su, Kai Shu, Naren Ramakrishnan, Liang Zhao·· 4 小时前AI 评分41
EpiWorld：将 LLM 政策智能体锚定在流行病学世界模型中
EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models
AI 导读
EpiWorld 是一个闭环框架，将 LLM 政策智能体锚定在学习到的动作条件流行病学世界模型和分层技能库上，在 COVID-19 与 Influenza 回顾性数据集上，该世界模型取得所有预测基线中最佳的分布外 Peak-MAE，闭环框架将累计住院人数最多降低 59%，在六个 LLM 主干上平均降低约 16%，优于强化学习和最优控制策略基线。
正文
Abstract: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.
| Comments: | Accepted to Findings of EMNLP 2026. 22 pages |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.02744 [cs.CL] |
| (or arXiv:2610.02744v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02744 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zeeshan Memon [view email]
[v1]
Fri, 2 Oct 2026 03:16:28 UTC (12,760 KB)
来源：arXiv：cs.CL · arxiv.org