Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Marcelo Fernandez

Marcelo Fernandez

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

Crypto×4AI×4Game Theory×1Logic×1

Frequent co-authors

Marcelo Fernandez - TraslaIA1×

Research Timeline

2026
Agent Control Protocol: Admission Control for Agent Actions

The paper introduces Agent Control Protocol (ACP), a stateful temporal admission control mechanism that enforces behavioral properties over execution traces to prevent harmful patterns from individually valid agent requests.

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems

The paper proves that standard runtime enforcement mechanisms cannot detect systematic behavioral drift in autonomous agents, proposing a new Invariant Measurement Layer (IML) that restores observability by accessing the agent's generative model.

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

The paper introduces the concept of the atomic decision boundary, proving that for autonomous systems to guarantee execution-time admissibility, the decision and the resulting state transition must occur as a single, indivisible step.

Reconstructive Authority Model: Runtime Execution Validity Under Partial Observability

The paper introduces the Reconstructive Authority Model (RAM), a novel framework that proves execution validity by assessing state coverage rather than just state integrity, showing that existing attestation methods are insufficient.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIcs.GTRecentApr 24, 2026

Reconstructive Authority Model: Runtime Execution Validity Under Partial Observability

Marcelo Fernandez - TraslaIA

The paper introduces the Reconstructive Authority Model (RAM), a novel framework that proves execution validity by assessing state coverage rather than just state integrity, showing that existing atte…

View →
cs.AIcs.CRRecentApr 19, 2026

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems

Marcelo Fernandez

The paper proves that standard runtime enforcement mechanisms cannot detect systematic behavioral drift in autonomous agents, proposing a new Invariant Measurement Layer (IML) that restores observabil…

View →
cs.LOcs.AIcs.CRRecentApr 19, 2026

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

Marcelo Fernandez

The paper introduces the concept of the atomic decision boundary, proving that for autonomous systems to guarantee execution-time admissibility, the decision and the resulting state transition must oc…

View →
cs.CRcs.AIRecentMar 19, 2026

Agent Control Protocol: Admission Control for Agent Actions

Marcelo Fernandez

The paper introduces Agent Control Protocol (ACP), a stateful temporal admission control mechanism that enforces behavioral properties over execution traces to prevent harmful patterns from individual…

View →