Towards Enforcing Company Policy Adherence in Agentic Workflows
This addresses the challenge of policy adherence for companies using LLM agents in workflows, though it appears incremental with preliminary results.
The paper tackles the problem of ensuring LLM agents reliably follow complex company policies in business process automation by introducing a deterministic, transparent, and modular framework that compiles policies into verifiable guard code and enforces compliance at runtime. It demonstrates preliminary results on the τ-bench Airlines domain.
Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company policies. In this study we introduce a deterministic, transparent, and modular framework for enforcing business policy adherence in agentic workflows. Our method operates in two phases: (1) an offline buildtime stage that compiles policy documents into verifiable guard code associated with tool use, and (2) a runtime integration where these guards ensure compliance before each agent action. We demonstrate our approach on the challenging $τ$-bench Airlines domain, showing encouraging preliminary results in policy enforcement, and further outline key challenges for real-world deployments.