Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems

• URL: http://arxiv.org/abs/2604.17511v2
• Date: Tue, 21 Apr 2026 18:00:40 GMT
• Title: Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems
• Abstract summary: We introduce the atomic decision boundary, a structural property of admission control systems.<n>We distinguish two classes: atomic systems and split evaluation systems.<n>We prove via a counterexample trace that no construction can make a split system equivalent to an atomic system with respect to admissibility.
• Score: 0.4929694290403903
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous systems increasingly execute actions that directly modify shared state, creating an urgent need for precise control over which transitions are permitted to occur. Existing governance mechanisms evaluate policies prior to execution or reconstruct behavior post hoc, but do not enforce admissibility at the exact moment a state transition is committed. We introduce the atomic decision boundary, a structural property of admission control systems in which the decision and the resulting state transition are jointly determined as a single indivisible step in the labeled transition system (LTS) model of execution. We distinguish two classes: atomic systems, where evaluation and transition are coupled within a single LTS step, and split evaluation systems, where they are separate transitions interleaved by environmental actions. The separation introduces an architectural gap -- the decision is evaluated in one system state; the transition fires in a potentially different one -- that no policy, regardless of sophistication, can close from within a split architecture. Under realistic concurrent environments, we prove via a constructive counterexample trace that no construction can make a split system equivalent to an atomic system with respect to admissibility. Three corollaries follow: impossibility of execution-time guarantees in split systems, insufficiency of external state enrichment, and admissibility as an execution-time rather than evaluation-time property. We further formalize the Escalate outcome -- absent from classical TOCTOU analyses -- proving that it transfers rather than eliminates the atomicity requirement: resolution is safe if and only if it is itself atomic. We classify RBAC, ABAC, OPA, Cedar, and AWS IAM as split systems and ACP as atomic, providing a structural taxonomy of existing governance mechanisms. Admissibility is a property of execution, not evaluation.

Related papers

• ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study [31.080136605890004]
  ASTELD is an operational six-axis classification framework for autonomous AI agents.<n>It is constructed by synthesizing prior agent with observable platform properties and explicit category-native rules.
  arXiv  Detail & Related papers  (2026-08-05T05:05:20Z)
• Constraint-Driven Synthesis of Hyper Petri Nets [46.9047309711542]
  This paper addresses the modeling and synthesis of constrained robotic system behaviors using Petri nets (PNs)<n>It investigates how to construct models in which all observable system states satisfy given logical constraints while remaining consistent with executable transition semantics.<n>The proposed method introduces an explicit execution semantics over observable states, induced by admissible (atomic) firing sequences.
  arXiv  Detail & Related papers  (2026-07-24T07:57:19Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems [0.4929694290403903]
  We introduce a runtime execution model in which authority is evaluated at action time and execution is conditioned on its constructibility.<n>We show that this model guarantees safety -- no action is executed without constructible authority -- and conditional liveness.
  arXiv  Detail & Related papers  (2026-04-24T13:32:09Z)
• Governed Auditable Decisioning Under Uncertainty: Synthesis and Agentic Extension [0.0]
  When automated decision systems fail, organizations often discover that formally compliant governance infrastructure cannot reconstruct what happened or why.<n>This paper synthesizes an operational governance evidence framework into an integrated chain and analytically assesses its transferability across four decision system architectures.
  arXiv  Detail & Related papers  (2026-04-21T05:45:04Z)
• Modeling and Simulation Based Engineering in the Context of Cyber-Physical Systems [51.82266520875928]
  Execution semantics are not treated as first-class engineering entities.<n>Modeling and Simulation Based Engineering organizes engineering around an iterative cycle alternating formal execution, experimental execution, verification, and activity-mediated validation.<n>These applications show that the framework generalizes beyond CPS to any system whose behavior depends on explicitly defined execution conditions.
  arXiv  Detail & Related papers  (2026-04-13T12:42:12Z)
• Governed Reasoning for Institutional AI [0.0]
  Cognitive Core is a governed decision substrate built from nine typed cognitive primitives.<n>Human review is a condition of execution rather than a post-hoc check.<n>We benchmark three systems on an 11-case balanced prior authorization appeal evaluation set.
  arXiv  Detail & Related papers  (2026-04-12T14:09:18Z)
• OpenKedge: Governing Agentic Mutation with Execution-Bound Safety and Evidence Chains [2.124730017640531]
  We introduce OpenKedge, a protocol that redefines mutation as a governed process.<n>Intent-to-Execution Evidence Chain (IEEC) links intent, context, policy decisions, execution bounds, and outcomes into a unified lineage.<n>We evaluate OpenKedge across multi-agent conflict scenarios and cloud infrastructure mutations.
  arXiv  Detail & Related papers  (2026-04-07T22:51:08Z)
• AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations [39.89241412792336]
  This paper presents AEGIS, a governance framework applicable to any healthcare AI system.<n>We implement a four-category deployment decision taxonomy (APPROVE, CONDITIONAL APPROVAL, CLINICAL REVIEW, REJECT) with an independent PMS ALARM signal.<n>Results demonstrate that AEGIS translates regulatory change-control concepts into executable governance procedures.
  arXiv  Detail & Related papers  (2026-03-20T11:56:59Z)
• Agent Control Protocol: Admission Control for Agent Actions [0.4929694290403903]
  Agent Control Protocol (ACP) is a formal specification for admission control governance of autonomous agents in B2B institutional environments.<n>ACP defines cryptographic identity, capability-based authorization, deterministic risk evaluation, chained delegation, and cryptographically-chained auditing.<n>ACP operates on top of RBAC and Zero Trust, addressing what neither model solves.
  arXiv  Detail & Related papers  (2026-03-19T12:28:28Z)
• Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI [45.21562889170875]
  We propose a systematic evaluation paradigm that characterizes agent trustworthiness over a scenario manifold.<n>The framework integrates four complementary components: static cognitive and policy analysis, (ii) interactive sandbox simulation, (iii) social-ethical alignment assessment, and (iv) a distribution-aware representative sampling engine.
  arXiv  Detail & Related papers  (2026-03-16T08:51:33Z)
• Self-Evolving Coordination Protocol in Multi-Agent AI Systems: An Exploratory Systems Feasibility Study [0.0]
  Self-Evolving Coordination Protocols (SECP)<n>SECP: coordination protocols that permit limited, externally validated self-modification.<n>This paper presents an exploratory systems feasibility study of Self-Evolving Coordination Protocols.
  arXiv  Detail & Related papers  (2026-02-02T14:45:04Z)
• LERA: Reinstating Judgment as a Structural Precondition for Execution in Automated Systems [1.4231914840649322]
  Judgment is typically introduced as an external intervention rather than a native precondition to execution.<n>This paper proposes LERA, a structural framework that enforces judgment as a mandatory, non-bypassable prerequisite for execution.
  arXiv  Detail & Related papers  (2026-01-12T14:39:55Z)
• The Loss of Control Playbook: Degrees, Dynamics, and Preparedness [39.39076397908963]
  This report addresses the absence of an actionable definition for Loss of Control (LoC) in AI systems by developing a novel taxonomy and preparedness framework.<n>We propose a graded LoC taxonomy, based on the metrics of severity and persistence, that distinguishes between Deviation, Bounded LoC, and Strict LoC.<n>We put forward a plan to maintain preparedness and prevent the occurrence of LoC outcomes should a state of societal vulnerability be reached.
  arXiv  Detail & Related papers  (2025-11-19T20:10:39Z)
• Behavior Trees vs Executable Ontologies: a Comparative Analysis of Robot Control Paradigms [51.56484100374058]
  We compare two approaches to modeling robotic behavior: imperative Behavior Trees (BTs) and declarative Executable Ontologies (EO)<n>BTs structure behavior hierarchically using control-flow, whereas EO represents the domain as a temporal, event-based semantic graph driven by dataflow rules.
  arXiv  Detail & Related papers  (2025-11-19T09:38:01Z)
• Subject-Event Ontology Without Global Time: Foundations and Execution Semantics [51.56484100374058]
  The formalization includes nine axioms (A1-A9), ensuring the correctness of executable: monotonicity of history (I1), acyclicity of causality (I2), traceability (I3)<n>The formalization is applicable to distributed systems, microservice architectures, DLT platforms, and multiperspectivity scenarios (conflicting facts from different subjects)<n>Special attention is given to the model-based approach (A9): event validation via schemas, actor authorization, automatic construction of causal chains (W3) without global time.
  arXiv  Detail & Related papers  (2025-10-20T19:26:44Z)
• Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning [44.17068570786194]
  We study Exo-MDPs, a structured class of Markov Decision Processes (MDPs)<n> Exogenous states evolve independently of the agent's actions, while endogenous states evolve deterministically based on both state components and actions.<n> Exo-MDPs are useful for applications including inventory control, portfolio management, and ride-sharing.
  arXiv  Detail & Related papers  (2024-09-22T18:45:38Z)
• Sufficient condition for universal quantum computation using bosonic circuits [44.99833362998488]
  We focus on promoting circuits that are otherwise simulatable to computational universality. We first introduce a general framework for mapping a continuous-variable state into a qubit state. We then cast existing maps into this framework, including the modular and stabilizer subsystem decompositions.
  arXiv  Detail & Related papers  (2023-09-14T16:15:14Z)
• A New Bandit Setting Balancing Information from State Evolution and Corrupted Context [52.67844649650687]
  We propose a new sequential decision-making setting combining key aspects of two established online learning problems with bandit feedback. The optimal action to play at any given moment is contingent on an underlying changing state which is not directly observable by the agent. We present an algorithm that uses a referee to dynamically combine the policies of a contextual bandit and a multi-armed bandit.
  arXiv  Detail & Related papers  (2020-11-16T14:35:37Z)

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.