图、循环与智能体框架工程：面向零信任智能体数据工程与分析处理
Graph, Loop, and Harness Engineering for Zero-Trust Agentic Data Engineering and Analytical Processing
浏览论文内容
中文总结 AI 辅助
针对云数据工程与分析中智能体协调可靠性问题，提出两个零信任框架，通过图、循环和智能体框架工程实现证据门控、有界恢复与零信任执行，实验验证了完成、恢复、授权及OLAP执行等指标。
中文摘要 AI 辅助
大型语言模型智能体日益自动化数据工作流，但端到端的云数据工程与分析执行要求在代码、数据、基础设施和运行时环境之间进行可靠协调。我们提出两个零信任框架。零信任智能体数据工程从自然语言任务生成、部署并验证完整的云数据工程解决方案，其完成条件基于仓库、部署、运行时和策略证据。零信任智能体OLAP将受治理的数据准备与经验证的联机分析处理（OLAP）相结合，仅在验证和证据约束的批准后才允许生产环境提升，并且仅在相同快照执行、精确结果等价、确定性基础和反思之后才发布分析答案。两个框架共享三个抽象：用于证据门控工作流结构的图工程、用于有界恢复的循环工程，以及用于零信任执行的智能体框架工程。我们在名义执行、受控故障、有界恢复和策略约束条件下评估这两个框架，测量已验证的完成、恢复、授权执行、生产提升和已验证的OLAP执行。
英文摘要
Large language model agents increasingly automate data workflows, but end-to-end cloud data engineering and analytical execution require reliable coordination across code, data, infrastructure, and runtime environments. We present two zero-trust frameworks. Zero-Trust Agentic Data Engineering generates, deploys, and verifies complete cloud data-engineering solutions from natural-language tasks, with completion conditioned on repository, deployment, runtime, and policy evidence. Zero-Trust Agentic OLAP combines governed Data Preparation with verified Online Analytical Processing (OLAP), permitting production promotion only after validation and evidence-bound approval, and releasing analytical answers only after Same-Snapshot Execution, Exact Result Equivalence, deterministic grounding, and reflection. Both frameworks share three abstractions: graph engineering for evidence-gated workflow structure, loop engineering for bounded recovery, and agent-harness engineering for zero-trust execution. We evaluate both frameworks under nominal execution, controlled failures, bounded recovery, and policy-constrained conditions, measuring verified completion, recovery, authorization enforcement, production promotion, and verified OLAP execution.
发表机构
- Tata Research Development and Design Centre（塔塔研发与设计中心）
机构由 AI 辅助整理，请以论文原文为准。
