[2605.07062] From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines

[2605.07062] From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines

arXiv - AI 4 min read

About this article

Abstract page for arXiv paper 2605.07062: From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines

Computer Science > Software Engineering arXiv:2605.07062 (cs) [Submitted on 8 May 2026] Title:From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines Authors:Marcus Emmanuel Barnes, Taher A. Ghaleb, Safwat Hassan View a PDF of the paper titled From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines, by Marcus Emmanuel Barnes and 2 other authors View PDF HTML (experimental) Abstract:AI agents are assuming active roles in Continuous Integration and Continuous Deployment (CI/CD) workflows, yet the research community lacks a shared vocabulary for describing what it means for CI/CD to be agentic, how much decision authority is delegated, and where control should reside. This paper presents a vision of agentic CI/CD in which the central challenge is not improving task performance but designing authority transfer, defined as the delegation of operational decisions from human-controlled pipelines to agent systems under specified constraints and recourse mechanisms. To structure this argument, we introduce a distinction between data-plane authority (localized interventions such as patch generation and test reruns) and control-plane authority (modifications to pipeline configuration, deployment policies, and approval gates). Drawing on research prototypes and industrial platforms, we show that current systems operate mainly at the data plane under bounded autonomy, with safety achieved through surrounding governance infrastructure rather t...

Originally published on May 11, 2026. Curated by AI News.

Related Articles

CUDA Proves Nvidia Is a Software Company | WIRED
Ai Infrastructure

CUDA Proves Nvidia Is a Software Company | WIRED

There’s a deep, forbidding moat that surrounds Nvidia—and it has nothing to do with hardware.

Wired - AI · 9 min ·
[2511.02805] MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
Llms

[2511.02805] MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning

Abstract page for arXiv paper 2511.02805: MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Lea...

arXiv - AI · 3 min ·
[2510.22944] Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies
Llms

[2510.22944] Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies

Abstract page for arXiv paper 2510.22944: Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies

arXiv - AI · 4 min ·
[2508.10880] Searching for Privacy Risks in LLM Agents via Simulation
Llms

[2508.10880] Searching for Privacy Risks in LLM Agents via Simulation

Abstract page for arXiv paper 2508.10880: Searching for Privacy Risks in LLM Agents via Simulation

arXiv - AI · 3 min ·
More in Ai Infrastructure: This Week Guide Trending

No comments

No comments yet. Be the first to comment!

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Daily or weekly digest • Unsubscribe anytime