# SHIELDS: Automating OS Hardening with Iterative Multi-Agent Remediation

arXiv: https://arxiv.org/abs/2606.05476 · HTML: https://mlsanity.com/paper/2606.05476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 5 of 5)

- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2604.12374/) (2026)
- [A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback](https://mlsanity.com/paper/2405.15690/) (2024)
- [GenKubeSec: LLM-Based Kubernetes Misconfiguration Detection, Localization, Reasoning, and Remediation](https://mlsanity.com/paper/2405.19954/) (2024)
- [Practically implementing an LLM-supported collaborative vulnerability remediation process: a team-based approach](https://mlsanity.com/paper/2409.14058/) (2024)

## Abstract (arXiv)

Security misconfigurations remain a leading cause of OS-level compromise, and manually keeping systems compliant with standards like Defense Information Systems Agency (DISA) Security Technical Implementation Guides (STIGs) is a tedious and expensive process. Existing compliance automation tools can reduce some of this burden, but they depend on static, pre-written corrective actions. In this paper, we introduce SHIELDS, a multi-agent system that uses large language models (LLMs) to approach OS hardening as an iterative, feedback-driven process. Instead of applying fixed remediations, SHIELDS continuously proposes fixes and refines them based on feedback from target system execution and validation scans. We evaluate the system across multiple virtual machine configurations using six contemporary LLMs ranging from 20B to 400B parameters, and find that SHIELDS successfully remediates up to 73% of scan findings. Our results also suggest that success in this setting depends less on model size (parameter count) than on effective tool use and information gathering, paving a practical path toward reducing the burden of security compliance in environments where compute is limited or security and privacy needs drive local model use.