# Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents

arXiv: https://arxiv.org/abs/2607.11346 · HTML: https://mlsanity.com/paper/2607.11346/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 17 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 13 of 13)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows](https://mlsanity.com/paper/2403.11322/) (2024)
- [SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints](https://mlsanity.com/paper/2503.08669/) (2025)
- [FlowAgent: Achieving Compliance and Flexibility for Workflow Agents](https://mlsanity.com/paper/2502.14345/) (2025)
- [SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs](https://mlsanity.com/paper/2501.09316/) (2025)
- [InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents](https://mlsanity.com/paper/2601.03204/) (2026)

## Built on by (most cited first, 4 of 4)

- [STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control](https://mlsanity.com/paper/2608.22538/) (2026)
- [How Strongly Should Task State Influence an LLM Agent?](https://mlsanity.com/paper/2609.25686/) (2026)
- [HEXIS: Compiling Agent Skills into Extended Finite State Machines](https://mlsanity.com/paper/2609.30123/) (2026)
- [Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?](https://mlsanity.com/paper/2609.39578/) (2026)

## Abstract (arXiv)

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.