VISA：面向智能体可复现性的智能体仿真模型结构化描述协议

中文摘要 AI 辅助

智能体模型（ABMs）难以复现：其行为分散在散文式叙述、特定平台代码和隐含假设中，导致两名读者常从相同文档中重构出不同模型。我们提出VISA，一种结构化、基于符号的描述协议，依据最小化且完备的原则，在八个相互关联的表格中指定模型——四个处于智能体层面（智能体、变量、感知、内部函数），四个处于模型层面（关联数据、输入/输出、调度、验证）。VISA通过两种产物使模型可被机器解析且无歧义：19条可执行一致性规则，将模型有效性转化为可检查属性；以及三种可复用的大语言模型（LLM）可执行技能（创作、检查、代码生成），将完整的作者-检查-代码-复现循环付诸实施。我们在三个外部、独立编写的、涵盖三个平台的ABMs上验证该协议：我们直接从其VISA规范复现了两个跨语言（NetLogo到Python）的模型，并在八个表格中捕获了第三个工业级AnyLogic模型（通过全部19条规则），同时如实界定了专有运动库和不可用数据阻碍复现的地方——这本身就是一项透明性贡献。VISA将复现障碍从不可见的模型转移到已命名、本地化的依赖项，使其可被处理。

英文摘要

Agent-based models (ABMs) are difficult to reproduce: their behavior is spread across prose narratives, platform-specific code, and implicit assumptions, so that two readers routinely reconstruct different models from the same documentation. We present VISA, a structured, symbol-based description protocol that specifies a model in eight interconnected tables---four at the agent level (Agent, Variable, Sensing, Internal Function) and four at the model level (Associated Data, Input/Output, Schedule, Validation)---under the principle of minimality with completeness. VISA makes a model machine-parseable and unambiguous via two artifacts: nineteen executable consistency rules that turn model validity into a checkable property, and three reusable LLM-executable skills (authoring, checking, and code generation) that operationalize the full author--check--code--reproduce loop. We validate the protocol on three external, independently authored ABMs spanning three platforms: we reproduce two cross-language (NetLogo to Python) directly from their VISA specifications, and we capture a third, an industrial AnyLogic model, in eight tables (passing all nineteen rules) while honestly demarcating where reproduction is blocked by a proprietary movement library and unavailable data---itself a transparency contribution. VISA moves the reproduction barrier from the model, where it is invisible, to a named, localized dependency, where it is actionable.

发表机构

• University of Chinese Academy of Sciences（中国科学院大学）

机构由 AI 辅助整理，请以论文原文为准。