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.

翻译：大型语言模型智能体从多种来源接收指令——系统消息、用户提示、工具输出、其他智能体等——每种来源承载着不同的信任与权威级别。当这些指令冲突时，智能体必须可靠地遵循最高权限指令以保持安全性和有效性。当前主流的指令层级范式假设存在由刚性角色标签（例如系统 > 用户）定义的固定且少量的权限级别（通常少于五个）。这无法满足现实智能体场景的需求，在这些场景中，冲突可能源于远更多种类的来源和上下文。本文提出多层指令层级结构（ManyIH），一种用于解决任意多权限级别指令间冲突的新范式。我们引入ManyIH-Bench，这是首个针对多层指令层级结构的基准测试。ManyIH-Bench要求模型在多达12层具有不同权限的冲突指令中进行导航，包含853个智能体任务（427个编程任务与426个指令遵循任务）。该基准通过大语言模型生成并经人工验证的约束条件，构建了覆盖46个现实智能体的高难度测试案例。实验表明，当指令冲突规模扩大时，即使当前最前沿的模型也表现不佳（准确率约40%）。本研究凸显了在智能体场景中专门针对细粒度、可扩展的指令冲突解决方法需求的紧迫性。