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

Abstract:Policy-governed agents must interpret case evidence while following an authorized procedure. We present \textsc{Stage}, an executable-graph framework that confines model judgment to policy-scoped nodes while placing procedural control in deterministic code. At each node, the model receives task-relevant policy context and returns a typed result, while the coordinator enforces the reviewed execution contract. We evaluate \textsc{Stage} on SOP-Bench Referral Abuse, two $\tau^2$-bench domains, and Smart Dispute, a proprietary banking benchmark. Compared with monolithic full-policy execution, \textsc{Stage} generally improves task success and repeated-run reliability across workflows of varying procedural complexity. The largest gains occur on the deeper Telecom and Smart Dispute workflows, where $\mathrm{Pass}^3$ increases by 7.5--55.0 and 57.2--65.7 percentage points, respectively, depending on the model. These results show that combining policy-scoped context with deterministic procedural control can improve the reliability of policy execution.

Artificial Intelligence (cs.AI)

arXiv:2608.22538 [cs.AI]

(or arXiv:2608.22538v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.22538 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.