发表机构
MIT（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Carnot，一款可解释交互式的AI分析执行引擎，可编译自然语言查询为执行图，支持用户干预流程并优化成本与延迟，助力企业高效获取可验证数据洞察。
AI 中文摘要
企业越来越多地通过语义算子、深度研究智能体等AI驱动工具，使用自然语言查询数据湖。然而，深度研究智能体是不透明的黑盒，隐藏了中间推理和数据检索步骤，也未提供管理API成本与执行延迟的控制手段；而语义算子对企业级数据湖而言可能成本过高。因此，使用这些系统的分析师无法干预幻觉前提、验证中间结果或纠正系统轨迹。本文提出Carnot，一款AI驱动分析的交互式执行引擎，它将自然语言请求编译为物理执行图，并通过交互式笔记本界面呈现。用户无需盲目等待最终输出，可对执行计划提出批评、增量执行算子、检查中间数据，或直接编辑底层代码或语义算子指令。Carnot的查询优化器会根据用户设定的成本或延迟约束优化查询。演示将展示Carnot如何助力用户在真实企业用例驱动的工作负载上获得高效且可验证的见解。
英文摘要
Enterprises increasingly seek to query data lakes using natural language via AI-driven tools like semantic operators or deep research agents. However, the latter operates as an opaque black box, hiding its intermediate reasoning and data retrieval steps, and failing to expose controls for managing API costs and execution latency. Meanwhile, the former can be prohibitively expensive for enterprise-scale data lakes. Consequently, analysts using these systems lack the agency to intercept hallucinated premises, verify intermediate results, or correct the system's trajectory. We present Carnot, an interactive execution engine for AI-driven analytics. Carnot compiles natural language requests into physical execution graphs and surfaces them through an interactive notebook interface. Rather than waiting blindly for a final output, users can critique the plan, incrementally execute operators, inspect intermediate data, or directly edit the underlying code or semantic operator instructions. Carnot's query optimizer will optimize the query with respect to cost or latency constraints provided by the user. Our demo will showcase how Carnot helps users achieve efficient and verifiable insights on workloads motivated by real enterprise use cases.
Comments4 pages, 2 figures, published as a demo paper in VLDB 2026
Journal refProceedings of the VLDB Endowment, Vol. 19, No. 12 pages 4642 - 4645, 2026
