# Many-Tier Instruction Hierarchy in LLM Agents

Source: [Many-Tier Instruction Hierarchy in LLM Agents](<https://www.sota2.com/research/paper/69dc78a27d0172140ec78c04>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-18T06:00:01.521Z

Authors: Jingyu Zhang, Tianjian Li, William Jurayj, Hongyuan Zhan, Benjamin Van Durme, Daniel Khashabi

Published: 2026-04-10T16:00:04.000Z

## Abstract

Large language model agents receive instructions from many sources-system messages, user prompts, tool outputs, other agents, and more-each carrying different levels of trust and authority. When these instructions conflict, agents must reliably follow the highest-privilege instruction to remain safe and effective. The dominant paradigm, instruction hierarchy (IH), assumes a fixed, small set of privilege levels (typically fewer than five) defined by rigid role labels (e.g., system \> user). This is inadequate for real-world agentic settings, where conflicts can arise across far more sources and contexts. In this work, we propose Many-Tier Instruction Hierarchy (ManyIH), a paradigm for resolving instruction conflicts among instructions with arbitrarily many privilege levels. We introduce ManyIH-Bench, the first benchmark for ManyIH. ManyIH-Bench requires models to navigate up to 12 levels of conflicting instructions with varying privileges, comprising 853 agentic tasks (427 coding and 426 instruction-following). ManyIH-Bench composes constraints developed by LLMs and verified by humans to create realistic and difficult test cases spanning 46 real-world agents. Our experiments show that even the current frontier models perform poorly (~40% accuracy) when instruction conflict scales. This work underscores the urgent need for methods that explicitly target fine-grained, scalable instruction conflict resolution in agentic settings.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Instruction Hierarchy Reasoning on MANYIH-BENCH coding](<https://www.sota2.com/research/sota/instruction-hierarchy-reasoning-on-manyih-bench-coding.md>): Instruction Hierarchy Reasoning; MANYIH-BENCH coding; Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.09443>)

[PDF](<https://arxiv.org/pdf/2604.09443.pdf>)

[Implementation](<https://github.com/JHU-CLSP/ManyIH>)