Abstract
Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs). We compile machine-readable SOP constraints into executable pseudo-code and run them with a program-guided (PG) stack machine that pages the active frame while an LLM performs semantic execution. A three-arm SOPBench study across six models separates representation from runtime: compiled text never significantly hurts and gains up to 16.0 points where official prose underperforms. Runtime guidance is capability-gated. Two strong models independently show positive seven-domain PG contrasts (58:19 and 75:31 discordant pairs), whereas weak models are harmed. A full-program cursor ablation (active frame first, complete program retained) recovers much of the strong-model refusal gain; selective visibility adds a smaller improvement. Paired probe and audit measurements track this divide to spontaneous state discipline rather than reconstruction ability. On Bank the three primary arms rise from 70.4 to 86.4 to 92.8, with 100% refusal correctness.
Practical Guidance
Compile first; enable active-frame paging only after a model-level discipline check.
Blogger's Review: This paper presents an innovative approach to optimize LLM execution through the compilation of SOPs combined with a PG stack machine. The findings indicate that capability-gated runtime guidance not only enhances the performance of strong models but also offers new insights for training and application in safety-critical domains. The integration of effective program design and execution strategies significantly boosts the overall system performance.