🛰️ Daily AI Frontier
‹ back to 2026-08-21

PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents

arXiv cs.AI LLM Agents Seongjae Kang, Taehyung Yu, Sung Ju Hwang 2026-08-20

TL;DR - PolicyGuide compiles organizational policies into workflow graphs and proactively guides customer-service LLM agents through compliant multi-step procedures. It improves both action-level safety and procedural compliance across several service domains and model families.

  • At user-turn boundaries, a verifier uses persisted workflow state to reconcile open requests and recommend step-specific remediation.
  • On τ²-bench airline, retail, and telecom tasks, PolicyGuide increased mean Pass⁴ from 0.42 to 0.62 with GPT-5.4.
  • Telecom saw the largest improvement, from 0.19 to 0.61, reflecting its highly structured workflows.
  • The workflows transferred to Claude Sonnet 4.6 and Gemini 2.5 Pro and achieved the lowest observed adversarial attack-success rate.

view merged work →