# STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control

arXiv: https://arxiv.org/abs/2608.22538 · HTML: https://mlsanity.com/paper/2608.22538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 19 of 19)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [SkillX: Automatically Constructing Skill Knowledge Bases for Agents](https://mlsanity.com/paper/2604.04804/) (2026)
- [Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents](https://mlsanity.com/paper/2605.22166/) (2026)
- [SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents](https://mlsanity.com/paper/2506.08119/) (2025)
- [Towards Enforcing Company Policy Adherence in Agentic Workflows](https://mlsanity.com/paper/2507.16459/) (2025)
- [Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents](https://mlsanity.com/paper/2603.20449/) (2026)
- [Beyond IVR: Benchmarking Customer Support LLM Agents for Business-Adherence](https://mlsanity.com/paper/2601.00596/) (2026)
- [AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents](https://mlsanity.com/paper/2607.02599/) (2026)
- [On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents](https://mlsanity.com/paper/2603.12109/) (2026)
- [PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents](https://mlsanity.com/paper/2606.29225/) (2026)
- [From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents](https://mlsanity.com/paper/2607.07321/) (2026)
- [Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents](https://mlsanity.com/paper/2607.11346/) (2026)
- [Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework](https://mlsanity.com/paper/2511.21686/) (2025)
- [PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents](https://mlsanity.com/paper/2608.19861/) (2026)
- [Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows](https://mlsanity.com/paper/2606.06923/) (2026)
- [COVENANT: Natural-Language Workflow Compilation for Aligned Agent Execution](https://mlsanity.com/paper/2607.25400/) (2026)

## Abstract (arXiv)

Policy-governed agents must interpret case evidence while reliably following authorized procedures. We present STAGE, an executable-graph framework that confines model judgment to policy-scoped nodes while placing procedural control in deterministic code. We evaluate STAGE on three public policy-following benchmarks and Smart Dispute, a proprietary banking benchmark. Compared with monolithic full-policy execution, STAGE improves task success and repeated-run reliability, with its largest observed gains on the deeper workflows. On τ2-bench Telecom and Smart Dispute, Pass3 improves by up to 55.0 and 65.7 percentage points, respectively. These results demonstrate the value of combining localized policy reasoning with deterministic procedural control for enterprise use.