# Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components

arXiv: https://arxiv.org/abs/2506.02357 · HTML: https://mlsanity.com/paper/2506.02357/

## Key facts

- Cited by 2 papers in the map (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 30 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## 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, 14 of 14)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)
- [AI Safety Gridworlds](https://mlsanity.com/paper/1711.09883/) (2017)
- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents](https://mlsanity.com/paper/2309.09919/) (2023)
- [AI Governance to Avoid Extinction: The Strategic Landscape and Actionable Research Questions](https://mlsanity.com/paper/2505.04592/) (2025)

## Built on by (most cited first, 2 of 2)

- [How Semantically Stable Are LLM Refusals? Measuring Confusion in Local Safety Boundaries](https://mlsanity.com/paper/2512.01037/) (2025)
- [Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory](https://mlsanity.com/paper/2609.03450/) (2026)

## Abstract (arXiv)

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these conflict with operational goals. This paper introduces a lightweight, interpretable benchmark to evaluate an LLM agent's ability to uphold a high-level safety principle when faced with conflicting task instructions. Our evaluation of six LLMs reveals two primary findings: (1) a quantifiable "cost of compliance" where safety constraints degrade task performance even when compliant solutions exist, and (2) an "illusion of compliance" where high adherence often masks task incompetence rather than principled choice. These findings provide initial evidence that while LLMs can be influenced by hierarchical directives, current approaches lack the consistency required for reliable safety governance.