How Can AI Find My Model? A Model-Finding Experimental Study Considering Data Formats, Embeddings, and Retrieval Strategies

AI 如何找到我的模型？一项关于数据格式、嵌入和检索策略的模型发现实验研究

Abstract: Discovering simulation models for reuse remains a fundamental challenge in Modeling and Simulation (M&S). When many models coexist, identifying those that align with a given modeling intent remains difficult. Recent advances in Artificial Intelligence (AI), particularly retrieval-based approaches, offer a promising pathway to operate at this semantic layer.

摘要： 在建模与仿真（M&S）领域，发现可重用的仿真模型始终是一项基础性挑战。当存在大量模型时，识别出符合特定建模意图的模型依然困难。人工智能（AI）的最新进展，特别是基于检索的方法，为在语义层面解决这一问题提供了有前景的途径。

In this paper, we present an experimental study investigating the impact of data representation, transformer-based embedding models, and retrieval strategies on the discovery of simulation models using natural language queries. We evaluated performance across multiple query types using standard information retrieval metrics, including recall@5 and nDCG@5.

在本文中，我们进行了一项实验研究，探讨了数据表示、基于 Transformer 的嵌入模型以及检索策略对使用自然语言查询发现仿真模型的影响。我们使用标准信息检索指标（包括 recall@5 和 nDCG@5）评估了多种查询类型的性能。

Results show that data representation matters, open-source embedding models can achieve high performance, and reranking methods are important, especially as query complexity increases. This work provides a baseline for AI-driven model discovery and discusses its role in advancing toward AI-driven composability and interoperability.

结果表明，数据表示至关重要，开源嵌入模型能够实现高性能，且重排序（reranking）方法非常重要，尤其是在查询复杂度增加时。这项工作为 AI 驱动的模型发现提供了基准，并探讨了其在推动 AI 驱动的可组合性和互操作性方面的作用。

---

Paper Details:

• Authors: Jhon G. Botello, Jose J. Padilla, Erika Frydenlund, Krzysztof Rechowicz, Eric Weisel
• arXiv ID: 2606.30846
• Subject: Artificial Intelligence (cs.AI)
• Submission Date: 29 Jun 2026

论文详情：

• 作者： Jhon G. Botello, Jose J. Padilla, Erika Frydenlund, Krzysztof Rechowicz, Eric Weisel
• arXiv ID： 2606.30846
• 学科： 人工智能 (cs.AI)
• 提交日期： 2026 年 6 月 29 日