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

• URL: http://arxiv.org/abs/2605.07062v1
• Date: Fri, 08 May 2026 00:15:43 GMT
• Title: From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines
• Abstract summary: This paper presents a vision of agentic Continuous Integration and Continuous Deployment (CI/CD) in which the central challenge is not improving task performance but designing authority transfer.<n> Drawing on research prototypes and industrial platforms, we show that current systems operate mainly at the data plane under bounded autonomy.<n>We identify three recurring patterns: constrained autonomy as the dominant design, external governance as the primary safety mechanism, and a widening gap between deployment momentum and evaluation methodology.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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 than intrinsic agent guarantees. We identify three recurring patterns: constrained autonomy as the dominant design, external governance as the primary safety mechanism, and a widening gap between deployment momentum and evaluation methodology. We propose a research agenda in which control-plane safety and governance mechanisms represent the most urgent open problem, followed by formalization of autonomy boundaries, evaluation frameworks, and human--agent coordination.

Related papers

• Toward a Decision-Assurance Layer for AI-Assisted Flight Planning in Air Traffic Management [37.2360395854375]
  This paper proposes the AI Trust and Assurance Layer (ATAL), a model-agnostic decision assurance architecture.<n>ATAL evaluates whether AI-generated flight-planning outputs are sufficiently reliable for operational use.<n>Although demonstrated in aviation, the framework is also transferable to other safety-critical decision-support domains.
  arXiv  Detail & Related papers  (2026-09-11T21:32:05Z)
• Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities [38.499036085412094]
  Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring.<n>Yet, real-world adoption remains constrained not only by autonomy performance, but by the difficulty of integrating agentic behavior into professional work.<n>This position paper synthesizes the ambitions and lessons from two ongoing efforts: NAMUR and PERSIST.
  arXiv  Detail & Related papers  (2026-08-19T11:53:02Z)
• Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks [0.0]
  Guard Rail Validation (GRV) is a standardizable runtime architecture for intercepting and validating AI-driven decisions before execution.<n>We present the architecture, algorithmic procedures, O-RAN deployment model, and evaluate threat coverage against known AI/ML attacks in telecommunications.
  arXiv  Detail & Related papers  (2026-07-02T14:21:26Z)
• Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda [43.328395470827665]
  We argue that symbolic structures embedded in regulated industries should be treated as core architectural components.<n>We propose compliance-by-construction as a complementary paradigm to guardrail-based monitoring.<n>We call on the neuro-symbolic community to engage with regulated process automation as a high impact research domain.
  arXiv  Detail & Related papers  (2026-06-11T14:34:11Z)
• Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems [65.90791804095561]
  Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination amplifies a less explored risk.<n>Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined.<n>This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement.
  arXiv  Detail & Related papers  (2026-05-14T14:36:13Z)
• Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks [46.32011684548212]
  AI agents are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions.<n>This position paper discusses our vision for system-level defenses against indirect prompt injection attacks.
  arXiv  Detail & Related papers  (2026-03-31T17:15:46Z)
• Beyond detection: cooperative multi-agent reasoning for rapid onboard EO crisis response [39.146761527401424]
  Rapid identification of hazardous events is essential for next-generation Earth Observation missions.<n>Current monitoring pipelines are largely ground-centric, introducing latency due to downlink limitations, multi-source data fusion constraints, and the computational cost of exhaustive scene analysis.<n>This work proposes a hierarchical multi-agent architecture for onboard EO processing under strict resource and bandwidth constraints.
  arXiv  Detail & Related papers  (2026-03-20T11:20:03Z)
• The Controllability Trap: A Governance Framework for Military AI Agents [0.0]
  We propose the Agentic Military AI Governance Framework (AMAGF)<n>AMAGF is a measurable architecture structured around three pillars: Preventive Governance, Detective Governance, and Corrective Governance.<n>Its core mechanism, the Control Quality Score (CQS), is a composite real-time metric quantifying human control and enabling graduated responses as control weakens.
  arXiv  Detail & Related papers  (2026-03-03T20:48:01Z)
• Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents [0.0]
  Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language--leads to critical risks such as scope creep and open-loop failures.<n>This study proposes Agentic Problem Frames (APF), a systematic engineering framework that shifts focus from internal model intelligence to the structured interaction between the agent and its environment.
  arXiv  Detail & Related papers  (2026-02-22T06:32:32Z)
• From Prompt-Response to Goal-Directed Systems: The Evolution of Agentic AI Software Architecture [0.0]
  Agentic AI denotes an architectural transition from stateless, prompt-driven generative models toward goal-directed systems.<n>This paper examines this transition by connecting intelligent agent theories, with contemporary LLM-centric approaches.<n>The study identifies a convergence toward standardized agent loops, registries, and auditable control mechanisms.
  arXiv  Detail & Related papers  (2026-02-11T03:34:48Z)
• Institutional AI: A Governance Framework for Distributional AGI Safety [1.3763052684269788]
  We identify three structural problems that emerge from core properties of AI models.<n>The solution is Institutional AI, a system-level approach that treats alignment as a question of effective governance of AI agent collectives.
  arXiv  Detail & Related papers  (2026-01-15T17:08:26Z)
• Assured Autonomy: How Operations Research Powers and Orchestrates Generative AI Systems [18.881800772626427]
  We argue generative models can be fragile in operational domains unless paired with mechanisms that provide feasibility, robustness to distribution shift, and stress testing.<n>We develop a conceptual framework for assured autonomy grounded in operations research.<n>These elements define a research agenda for assured autonomy in safety-critical, reliability-sensitive operational domains.
  arXiv  Detail & Related papers  (2025-12-30T04:24:06Z)
• On the Regulatory Potential of User Interfaces for AI Agent Governance [27.951021158233587]
  We propose regulating user interfaces of AI agents as a way of enforcing transparency and behavioral requirements.<n>We analyze 22 existing agentic systems to identify UI elements that play key roles in human-agent interaction and communication.<n>Our work exposes a new surface for regulatory action that supplements previous proposals for practical AI agent governance.
  arXiv  Detail & Related papers  (2025-11-30T05:32:13Z)
• AI Agents with Decentralized Identifiers and Verifiable Credentials [32.505127447635864]
  This article presents a prototypical multi-agent system, where each agent is endowed with a self-sovereign digital identity.<n>It combines a unique and ledger-anchored Decentralized Identifier (DID) of an agent with a set of third-party issued Verifiable Credentials (VCs)<n>It enables agents at the start of a dialog to prove ownership of their self-controlled DIDs for authentication purposes and to establish various cross-domain trust relationships.
  arXiv  Detail & Related papers  (2025-10-01T08:10:37Z)
• Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions [30.046299694187855]
  Large language models (LLMs)-empowered autonomous agents are transforming both digital and physical environments by enabling adaptive, multi-agent collaboration.<n>We propose a blockchain-enabled layered architecture for regulatory agent collaboration, comprising an agent layer, a blockchain data layer, and a regulatory application layer.<n>Our approach establishes a systematic foundation for trustworthy, resilient, and scalable regulatory mechanisms in large-scale agent ecosystems.
  arXiv  Detail & Related papers  (2025-09-11T07:46:00Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.