A Proposal for an Agentic AI Architecture to Support Multi-Domain Decision-Making in the Brazilian Armed Forces

arXiv:2609.20080 · cs.AI, cs.MA · Submitted 2026-09-17 · Read on arXiv

cs.AI, cs.MA

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: This paper was accepted for publication in the XXVIII SIGE (Simpósio de Aplicações Operacionais em Áreas de Defesa)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Agentic AI — 17× in this paper · explained in 1 episode
• Core — 6× in this paper · explained in 2 episodes
• Multi-Agent System — 4× in this paper · explained in 6 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• RAG — 3× in this paper · explained in 3 episodes
• Agentic AI Framework — 2× in this paper · explained in 1 episode
• Artificial Intelligence — 2× in this paper
• Artificial Intelligence (AI) — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Aperture — 1× in this paper · explained in 1 episode
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes

Sources

• MobiLLM: An Agentic AI Framework for Closed-Loop Threat Mitigation in 6G Open RANs
• Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
• The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
• MalTool: Malicious Tool Attacks on LLM Agents
• A Framework for Formalizing LLM Agent Security
• On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
• Preventing Prompt Injection with Type-Directed Privilege Separation
• Prompt Injection Attack to Tool Selection in LLM Agents
• AgentWatcher: A Rule-based Prompt Injection Monitor
• Meta-SecAlign: Training LLMs against Prompt Injection for Robust Agents
• Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection