Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts

• URL: http://arxiv.org/abs/2605.12105v1
• Date: Tue, 12 May 2026 13:20:30 GMT
• Title: Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts
• Abstract summary: This work introduces a two-dimensional design space in which both dimensions are organised into five operational levels.<n> Autonomy ranges from human-commanded operation (L1) to fully autonomous monitoring (L5)<n>We propose six architectural tactics--checkpoints, escalation, multi-agent delegation, tool provisioning, tool fencing, and write staging--for adjusting a deployment's position within it.
• Score: 1.2031796234206136
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deploying agentic AI in regulated contexts requires principled reasoning about two design dimensions: agency (what the system can do) and autonomy (how much it acts without human involvement). Though often treated independently, they are coupled: at higher autonomy, human error correction is less available, so reliable operation requires constraining agency accordingly; compliance requirements reinforce this by mandating human involvement as action consequences grow. Yet no established approach addresses them jointly, leaving practitioners without a principled basis for reasoning about oversight, action consequences, and error correction. This work introduces a two-dimensional design space in which both dimensions are organised into five operational levels, making the coupling explicit and navigable. Autonomy ranges from human-commanded operation (L1) to fully autonomous monitoring (L5); agency ranges from reasoning over supplied context (L1) to committed writes to authoritative records (L5). Building on this space, we propose six architectural tactics--checkpoints, escalation, multi-agent delegation, tool provisioning, tool fencing, and write staging--for adjusting a deployment's position within it. The tactics are grounded in two worked examples from public-sector contexts, illustrating how they apply under realistic compliance constraints. We further examine five deployment parameters--model capability, agent architecture, tool fidelity, workflow bottlenecks, and evaluation--that shape what is achievable at any configuration independently of agency and autonomy. Together, the design space, tactics, and deployment parameters provide a shared vocabulary for principled, compliance-aware agentic AI design in which responsibility, auditability, and reversibility are explicit design considerations rather than properties that must be retrofitted after deployment.

Related papers

• Specifying the Delegated-Autonomy Boundary: Requirements Engineering for Agentic AI [5.421928928336395]
  Agentic AI systems plan, maintain state, and act in external environments with varying degrees of autonomy.<n>Current practices bury these decisions inside prompts, tool schemas, and runtime policies, even though they are requirements-level commitments.<n>This paper proposes two complementary artifacts: an Agency Justification Record and an Agentic Delegation Policy.
  arXiv  Detail & Related papers  (2026-07-19T12:27:39Z)
• The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning [65.67266333751569]
  Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.<n>We propose a self-supervised reinforcement learning framework that targets the internal reasoning process without requiring ground-truth annotations.<n>We show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and data domains.
  arXiv  Detail & Related papers  (2026-06-10T10:50:06Z)
• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
  We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
  arXiv  Detail & Related papers  (2026-06-03T20:02:35Z)
• HAAS: A Policy-Aware Framework for Adaptive Task Allocation Between Humans and Artificial Intelligence Systems [0.43748379918040853]
  Humans and AI routinely share tasks or take complementary roles depending on context, fatigue, and the stakes involved.<n>Human-AI Adaptive Symbiosis (HAAS) is an implemented framework for adaptive task allocation in software engineering and manufacturing.
  arXiv  Detail & Related papers  (2026-05-04T17:09:21Z)
• Position: agentic AI orchestration should be Bayes-consistent [92.04373485710285]
  This paper argues that coherent decision-making requires Bayesian principles at the orchestration level of the agentic system.<n>It provides examples and design patterns to illustrate how beliefs and utility-aware policies can improve agentic AI orchestration.
  arXiv  Detail & Related papers  (2026-05-01T15:43:43Z)
• 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)
• ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Intrinsic Adaptation [60.25542764389203]
  Agentic systems powered by Large Language Models (LLMs) have demonstrated remarkable potential in tackling complex, long-horizon tasks.<n>Existing approaches, relying on manual orchestration or runtime-based patches, often struggle with poor generalization and fragmented optimization.<n>We propose ToolSelf, a novel paradigm enabling tool-driven self-readjustment.
  arXiv  Detail & Related papers  (2026-02-08T09:27:18Z)
• 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)
• Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning [4.226647687395254]
  This paper presents a Responsible(RAI) and Explainable(XAI) AI Agent Architecture for production-grade agentic based on multi-model consensus and reasoning-layer governance.<n>In the proposed design, a consortium of heterogeneous LLM and VLM agents independently generates candidate outputs from a shared input context.<n>A dedicated reasoning agent then performs structured consolidation across these outputs, enforcing safety and policy constraints, mitigating hallucinations and bias, and producing auditable, evidence-backed decisions.
  arXiv  Detail & Related papers  (2025-12-25T14:49:25Z)
• Agentic Services Computing [51.50424046053763]
  We propose Agentic Services Computing, a paradigm that reimagines services as autonomous, adaptive, and collaborative agents.<n>We organize ASC around a four-phase lifecycle: Design, Deployment, Operation, and Evolution.
  arXiv  Detail & Related papers  (2025-09-29T07:29:18Z)
• Toward a Theory of Agents as Tool-Use Decision-Makers [89.26889709510242]
  We argue that true autonomy requires agents to be grounded in a coherent epistemic framework that governs what they know, what they need to know, and how to acquire that knowledge efficiently.<n>We propose a unified theory that treats internal reasoning and external actions as equivalent epistemic tools, enabling agents to systematically coordinate introspection and interaction.<n>This perspective shifts the design of agents from mere action executors to knowledge-driven intelligence systems, offering a principled path toward building foundation agents capable of adaptive, efficient, and goal-directed behavior.
  arXiv  Detail & Related papers  (2025-06-01T07:52:16Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)

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.