6 papers

cs.CR2026

Agent Control Protocol: Admission Control for Agent Actions

Marcelo Fernandez

Autonomous agents can produce harmful behavioral patterns from individually valid requests -- a threat class per-request policy evaluation cannot address, because stateless engines…

cs.AI2026

Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems

Marcelo Fernandez - TraslaIA

Autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime. Prior work defined Reconstructive Auth…

cs.CR2026

Reconstructive Authority Model: Runtime Execution Validity Under Partial Observability

Marcelo Fernandez - TraslaIA

Autonomous systems increasingly operate under partial observability where execution-relevant state is never fully accessible. Existing governance mechanisms -- trusted execution en…

cs.AI2026

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems

Marcelo Fernandez

Autonomous agent systems are governed by enforcement mechanisms that flag hard constraint violations at runtime. The Agent Control Protocol identifies a structural limit of such sy…

cs.LO2026

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

Marcelo Fernandez

Autonomous systems increasingly execute actions that directly modify shared state, creating an urgent need for precise control over which transitions are permitted to occur. Existi…

cs.LG2026

Pi-transformer: A prior-informed dual-attention model for multivariate time-series anomaly detection

Sepehr Maleki, Negar Pourmoazemi

Anomalies in multivariate time series often arise from temporal context and cross-channel coordination rather than isolated outliers. We present Pi-Transformer (Prior-Informed Tran…