arXiv AI By Jingyu Zhang, Tianjian Li, William Jurayj, Hongyuan Zhan, Benjamin Van Durme, Daniel Khashabi

Many-Tier Instruction Hierarchy in LLM Agents

Read the original on arXiv AI →

The paper introduces Many-Tier Instruction Hierarchy (ManyIH), a new framework for resolving conflicts among instructions with arbitrarily many privilege levels in large language model agents. It presents ManyIH-Bench, a benchmark featuring 853 agentic tasks that require navigating up to 12 levels of conflicting instructions across 46 real-world agents. Experiments show current models achieve only about 40% accuracy when instruction conflict scales, highlighting a gap in fine-grained, scalable conflict resolution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Aug 19

SkillEffect: Checked Lowering for Memory-Bounded Agent Tools

SkillEffect is a checked‑lowering runtime that ensures agent tool calls stay within memory limits by verifying each proposed program against an immutable input before execution. It uses audited relation plugins to provide source recognition, bounded intermediate representation construction, and postconditions, while a shared runtime handles selection, bounded VM execution, and atomic capacity leasing. Experiments across six operator families show that bounded access significantly reduces peak memory usage and improves completion rates under fixed memory caps.

By Yinuo Wang, Yiyu Shi