Sign InOpen Brain
arXivPaperNeeds Review

SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center

Sentinel-RL keeps topology outside the LLM: a graph encoder and constrained policy choose SOC actions, while the model writes critic-gated narratives for human approval.

arXiv · Sep 3, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Sentinel-RL compresses an authentication graph with a graph-attention encoder, maps that state to constrained actions using PPO, and limits the LLM to recommendations and analyst-readable narratives. Its full human-approved loop had a **6.3 s median** runtime.

Practical Implication

For security agents operating over large structured state, keep graph validity and action choice in deterministic or constrained components. Use the LLM at the semantic boundary, then place a critic and explicit approval before containment.

Agent-Ready Context
Sentinel-RL compresses an authentication graph with a graph-attention encoder, maps that state to constrained actions using PPO, and limits the LLM to recommendations and analyst-readable narratives. Its full human-approved loop had a **6.3 s median** runtime.

For security agents operating over large structured state, keep graph validity and action choice in deterministic or constrained components. Use the LLM at the semantic boundary, then place a critic and explicit approval before containment.

The reported results come from the **LANL dataset** and Indiana University’s Quartz cluster. Precision of **0.91** and recall of **0.87** were measured on labeled red-team events, not a broad production SOC deployment.
Connected Context · Feed7 Judgment

This provides domain-specific evidence for the prior pattern of moving structured reasoning and consequential actions out of the LLM: graph compression and constrained policy execution handle topology and containment, while the model explains and recommends. It adds an explicit critic-and-human approval loop, but narrows the evidence to labeled LANL red-team events on Quartz rather than production SOC generality; the 6.3 s median also makes the full loop’s latency concrete.

Semantic Blindness: 500,000 Sensors Confused an LLM - Raahul Singh & Vanč Levstik, PhaidraBoth separate semantic interpretation from large structured-state resolution; Sentinel-RL extends that boundary from deterministic entity lookup to graph encoding and constrained action selection.How Kepler Built Verifiable AI for Financial Services — Vinoo GaneshIt reinforces Kepler’s separation of model judgment from sensitive state mutation, applying the pattern to security containment and adding a critic plus human approval before execution.Your Agent Just Authorized What?! — Jay Mok & Ben Coumes, PaypalThe human-approved containment loop implements the candidate’s principle that consequential actions require stronger authorization, though the source does not describe the same scoped, time-bound mandate design.In Code They Act, In Proof We Trust — Erik Meijer, Leibniz LabsBoth place a machine-enforced gate between LLM recommendations and side effects; Sentinel-RL uses constrained actions and a critic rather than the candidate’s proposed machine-checkable safety proofs.
Context Map
agentsecuritydata#harness-engineering#tool-use#agent-reliability
Uncertainty
The reported results come from the **LANL dataset** and Indiana University’s Quartz cluster. Precision of **0.91** and recall of **0.87** were measured on labeled red-team events, not a broad production SOC deployment.