摘要：MongoDB 等文档数据库是现代应用的核心基础设施。面向这类数据库的自然语言接口——Text-to-MQL——可让非专业用户无需掌握查询语言，也能查询复杂的半结构化数据。这一任务的进展依赖于高质量基准，而最实用的获取方式，是将现有 Text-to-SQL 基准转换至文档数据库场景。遗憾的是，现有工作依赖启发式规则进行机械转换：文档模式映射关系数据库的外键图，每条查询也映射其源 SQL。实验结果显示，这些方法完全无法迁移 BIRD 的 21 个数据库中的 6 个；对于其他数据库，则会静默丢失最多 25.9% 的行数据，并且随着数据规模扩大，其模式对应的标准答案查询运行速度会慢一个数量级以上。为此，我们提出了一条转换流水线：由编码 Agent 驱动，并结合人在回路验证；该流水线根据预期访问模式设计每个文档模式，并将查询重写为 MongoDB 原生形式。我们将其应用于 BIRD，构建了一个基于访问模式的 Text-to-MQL 基准（AptMQL-Bench）。该基准包含 21 个面向文档的数据库、3,186 条自然语言请求及其对应的 MQL 查询；其中的数据库从 SQLite 迁移而来，未发生数据丢失，并且能够高效扩展。最强模型 Claude Opus 4.5 在不使用外部知识证据时仅达到 57.38% 的准确率，使用外部知识证据时达到 70.34%。这表明，真实场景下的 Text-to-MQL 生成仍然具有挑战性。

Abstract:Document databases such as MongoDB are core infrastructure for modern applications, and natural-language interfaces to them---text-to-MQL---would let non-experts query complex, semi-structured data without mastering the query language. Progress on this task depends on high-quality benchmarks, which are most practically obtained by converting an existing text-to-SQL benchmark to the document setting. Unfortunately, existing efforts rely on heuristics for mechanical conversion: the document schema mirrors the relational foreign-key graph, and each query mirrors its source SQL. As a result in our experiments, these approaches fail to migrate 6 of 21 BIRD databases outright, silently drop up to 25.9% of rows on others, and yield schemas whose ground-truth queries run over an order of magnitude slower as the data scales. We instead propose a conversion pipeline, driven by coding agents with human-in-the-loop verification, that designs each document schema from expected access patterns and rewrites queries to be MongoDB-native. Applying it to BIRD, we build an access-pattern-based text-to-MQL benchmark (AptMQL-Bench). It includes 21 document-oriented databases, 3,186 natural-language requests, and their associated MQL queries---whose databases are migrated from SQLite without data loss and scale efficiently. The strongest model, Claude Opus 4.5, achieves only 57.38% accuracy without external knowledge evidence and 70.34% with it. This indicates that realistic text-to-MQL generation remains challenging.