# Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees

arXiv: https://arxiv.org/abs/2610.18326 · HTML: https://mlsanity.com/paper/2610.18326/

## 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 14 of its 29 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection](https://mlsanity.com/paper/2304.00409/) (2023)
- [CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale](https://mlsanity.com/paper/2506.02548/) (2025)
- [CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service](https://mlsanity.com/paper/1805.01217/) (2018)
- [ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback](https://mlsanity.com/paper/2601.10156/) (2026)
- [Question Answering for Privacy Policies: Combining Computational and Legal Perspectives](https://mlsanity.com/paper/1911.00841/) (2019)
- [PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance](https://mlsanity.com/paper/2502.17041/) (2025)
- [Intent Classification and Slot Filling for Privacy Policies](https://mlsanity.com/paper/2101.00123/) (2021)
- [GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners](https://mlsanity.com/paper/2509.24418/) (2025)
- [SafeMT: Multi-turn Safety for Multimodal Language Models](https://mlsanity.com/paper/2510.12133/) (2025)
- [Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling](https://mlsanity.com/paper/2508.03296/) (2025)

## Abstract (arXiv)

Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an auto-regressive guardrail model remains challenging: such models incur high inference latency and are often poorly aligned with customized policies. To address these problems, we present Jev-Guard, a unified model for safety classification and policy routing. We further construct a policy tree over which Jev-Guard performs routing, spanning diverse domains including content moderation, cybersecurity, privacy, and legal compliance. Specifically, Jev-Guard first navigates the policy tree to select the applicable audit policy given the caller's audit context, and then performs safety classification conditioned on the retrieved policies. On 7,033 evaluation cases, Jev-Guard achieves 93.72% safety accuracy, a mean latency of 58ms, and 93.10% hierarchical routing accuracy. The full routing-and-classification pipeline averages 240ms. Furthermore, we integrate Jev-Guard into the Hermes harness framework. Across agent trajectories, its separate permission gate cuts mean review time per task from 4.80s for an SFT-LLM judge to 1.33s, with no policy violations are observed for either guard.