EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The Governance Gap in Contemporary LLM-Based Agentic Systems: A Structural Diagnostic Review

Christopher Valdez-Cantú, Jose Antonio Cantoral-Ceballos, Joanna Alvarado-Uribe

AI · 20.08.2026 · 7 (8) · 322

DOI: 10.3390/ai7080322 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 20.08.2026. Verfasst von Christopher Valdez-Cantú und 2 weiteren Autor:innen. Die Arbeit nennt 153 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tecnologico de Monterrey through the Open Access Publication Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) are increasingly integrated into agentic workflows that require extended reasoning, persistent state management, coordinated tool use, and controlled execution. As this operational scope expands, a central question emerges: whether probabilistic generation alone can reliably support coherent behavior across interacting system components. This paper addresses that question through a structural diagnostic review of contemporary agentic systems. Starting from LLM-based tutoring as an analytically demanding entry point and extending toward structurally related agent architectures, the paper draws on a five-phase review of N=145 research records. The analysis is organized through the Agentic Structure Taxonomy (AST), which structures the literature across four dimensions: Cognition, Interaction, Orchestration, and Governance. The review identifies five recurrent empirical problem patterns and uses them as abductive diagnostic cues for formulating seven cross-dimensional transition gaps that capture recurrent discontinuities at the boundaries between reasoning, state, control, and execution. From these gaps, fourteen structural constraints are derived across three control domains: state isolation, control alignment, and execution governance. These constraints are interpreted not as prescriptive design mandates, but as analytically derived conditions associated with reducing error propagation across subsystem transitions. The paper argues that reliability in agentic systems is shaped not only by model performance or prompt design, but also by whether the boundaries linking probabilistic reasoning to persistent state, orchestration, and execution are governed by explicit structural conditions.

Förderung

  • Tecnologico de Monterrey through the Open Access Publication Fund

Zitieren

APA

Valdez-Cantú, C., Cantoral-Ceballos, J. A., & Alvarado-Uribe, J. (2026). The Governance Gap in Contemporary LLM-Based Agentic Systems: A Structural Diagnostic Review. AI, 7(8), 322. https://doi.org/10.3390/ai7080322

Vancouver

Valdez-Cantú C, Cantoral-Ceballos JA, Alvarado-Uribe J. The Governance Gap in Contemporary LLM-Based Agentic Systems: A Structural Diagnostic Review. AI. 2026;7(8):322. doi:10.3390/ai7080322

BibTeX
@article{ValdezCant2026,
  author = {Valdez-Cantú, Christopher and Cantoral-Ceballos, Jose Antonio and Alvarado-Uribe, Joanna},
  title = {The Governance Gap in Contemporary LLM-Based Agentic Systems: A Structural Diagnostic Review},
  journal = {AI},
  year = {2026},
  volume = {7},
  number = {8},
  pages = {322},
  doi = {10.3390/ai7080322}
}
Kostenlos starten →