arXiv cs.CY· Nicol\`o Gozzi, Ciro Cattuto, Alessandro Vespignani·· 13 小时前AI 评分31
Epydemix Agent Framework：用 AI 智能体驱动流行病模型
Driving Epidemic Models with AI Agents: the Epydemix Agent Framework
AI 导读
Epydemix Agent Framework 在开源 Python 库 Epydemix 之上增加模型与参数发现、声明式场景预校验、经测试代码执行和结果可检查四项能力，让 AI 智能体无需写代码即可完成从自然语言场景描述到定量结果、图表与结论解读的全流程。在 50 次智能体会话、5 项建模任务的评估中，该框架在多数任务上减少了对话轮次、输出 token 和成本，除非以资源换取逐点可复现性。
正文 · 原文
Abstract:Artificial Intelligence agents based on large language models provide convenient natural language interfaces to scientific software, but reliability is not automatic. Here we introduce the Epydemix Agent Framework, an additive layer over Epydemix, an open-source Python library for stochastic compartmental epidemic modeling. The framework extends the library with four capabilities to facilitate interaction with an AI agent: discovery of available models and parameters, preventive validation of a declarative scenario specification, execution through tested library code, and inspectability of results. These capabilities let an agent handle the entire modeling process, from the natural-language description of the scenario to quantitative results, figures, and interpretation of findings without writing custom code. Each step reads input files and saves results in a separate output bundle, making the process auditable and reproducible. First, we show the end-to-end workflow with a case study comparing vaccination strategies for a novel respiratory virus. Second, we assessed the framework across 50 agent sessions and five modeling tasks by comparing the agent use of the framework against the direct use of the Python interface. The framework reduced turns, output tokens, and cost on most tasks, unless it trades resources for per-point reproducibility.
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2609.28692 [cs.AI] |
| (or arXiv:2609.28692v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.28692 arXiv-issued DOI via DataCite |
Submission history
From: Nicolò Gozzi [view email]
[v1]
Wed, 23 Sep 2026 18:31:43 UTC (557 KB)
[v2]
Wed, 21 Oct 2026 21:17:05 UTC (556 KB)
来源：arXiv cs.CY · arxiv.org