POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automation

TL;DR

POLARIS introduces a governance framework for agentic AI in enterprise back-office automation, ensuring policy compliance, auditability, and predictability through typed planning and validated execution, with promising empirical results.

Contribution

It presents POLARIS, a novel framework combining typed plan synthesis, policy-guided reasoning, and guarded execution to improve agentic AI in enterprise settings.

Findings

Achieves 0.81 micro F1 on SROIE dataset.

Attains 0.95 to 1.00 precision in synthetic anomaly routing.

Provides initial benchmarks for governed agentic AI.

Abstract

Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic Reasoning for Integrated Systems), a governed orchestration framework that treats automation as typed plan synthesis and validated execution over LLM agents. A planner proposes structurally diverse, type checked directed acyclic graphs (DAGs), a rubric guided reasoning module selects a single compliant plan, and execution is guarded by validator gated checks, a bounded repair loop, and compiled policy guardrails that block or route side effects before they occur. Applied to document centric finance tasks, POLARIS produces decision grade artifacts and full execution traces while reducing human intervention. Empirically, POLARIS achieves a micro F1 of 0.81 on the SROIE dataset and, on a controlled synthetic suite, achieves 0.95 to 1.00 precision for anomaly routing with preserved audit trails. These evaluations constitute an initial benchmark for governed Agentic AI. POLARIS provides a methodological and benchmark reference for policy-aligned Agentic AI. Keywords Agentic AI, Enterprise Automation, Back-Office Tasks, Benchmarks, Governance, Typed Planning, Evaluation