面向智能体云工程：零信任 Agent Harness 下的图工程与循环工程

View PDF HTML (experimental)

Abstract:Agentic AI is enabling cloud-based workflows in which autonomous agents reason over operational state, invoke authorized tools, modify software and infrastructure, deploy services, verify execution outcomes, and adapt across long-horizon, multistep tasks. Engineering such workflows requires explicit mechanisms for workflow progression, constrained execution, failure recovery, and verifiable completion. We present Agentic Cloud Workflow Engineering, an agentic AI framework that transforms natural-language agentic cloud-engineering tasks into validated code repositories and verified operational cloud deployments for automating cloud-based agentic workflows. The framework separates three complementary concerns: graph engineering specifies long-horizon workflow progression and verification-dependent transitions; loop engineering provides bounded diagnosis, repair or re-planning, retry, and re-verification; and agent harness engineering enforces zero-trust execution through identity, authorization, policy-scoped capabilities, isolation, and runtime safeguards. Workflow progression and completion require machine-checkable repository, deployment, and runtime evidence, with recovery constrained by explicit operational bounds and termination criteria. We instantiate the framework on Google Cloud and evaluate repository completeness, controlled execution, evidence-gated progression, operational deployment, and bounded recovery. Experimental results show that executions terminate with either a verified operational cloud deployment or an auditable terminal failure under bounded recovery. The framework provides a unified engineering architecture for cloud-based workflows spanning Agentic DevOps, Agentic CloudOps, Agentic SRE/AIOps, Agentic SecOps, Agentic DataOps, Agentic MLOps/LLMOps, AgentOps, Agentic RAG/GraphRAG, and related cloud-engineering domains.

Comments:	Nil
Subjects:	Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2609.00050 [cs.SE]
	(or arXiv:2609.00050v2 [cs.SE] for this version)
	https://doi.org/10.48550/arXiv.2609.00050 arXiv-issued DOI via DataCite

Submission history

From: Sagar Srinivas Sakhinana [view email]
[v1] Sun, 30 Aug 2026 07:20:49 UTC (35 KB)
[v2] Fri, 16 Oct 2026 06:01:51 UTC (43 KB)