🤖 AI Summary
This study addresses the reproducibility challenges in agent-based simulation models, which often stem from fragmented descriptions, implicit assumptions, and platform dependencies. To overcome these issues, the authors propose the VISA protocol, which standardizes model documentation into eight interconnected, machine-readable tables that explicitly distinguish between reproducible and non-reproducible components. The approach integrates 19 executable consistency rules with three capabilities of large language models—writing, verification, and code generation—to enable structured, verifiable, and automatically implementable model specifications. Empirical validation demonstrates successful cross-language reproduction of two agent-based models and the complete structural formalization of an industrial-scale AnyLogic model, clearly exposing reproducibility barriers caused by proprietary libraries and missing data, thereby significantly enhancing model transparency and operational utility.
📝 Abstract
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.