Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

PolicyGuide: A New Framework to Enforce Policy Compliance in LLM Agents Across Entire Workflows

AI By Crimson AI Hugging Face Papers 22 August 2026 · 00:00 20 views
Share: X Telegram

Hugging Face researchers introduce PolicyGuide, a framework that compiles domain policies into workflow graphs and uses a proactive verifier to guide LLM agents through compliant multi-step procedures, boosting Pass^4 scores significantly across benchmark domains.

PolicyGuide: A New Framework to Enforce Policy Compliance in LLM Agents Across Entire Workflows

Key points

Customer-service LLM agents are increasingly tasked with acting on behalf of users, but ensuring they adhere to organizational policies remains a challenge. Compliance failures can stem from forbidden actions, like granting an ineligible change, or from omitting procedural requirements, such as user identification or confirmation. Existing runtime safeguards often intervene only on individual risky actions, lacking the ability to guide agents through complex, multi-step procedures.

To address this, researchers from Hugging Face have introduced PolicyGuide, a novel framework that compiles each domain policy into a workflow graph. At every user-turn boundary, a proactive verifier uses the persisted graph state to reconcile open requests and provide step-specific remediation, steering the agent along a policy-compliant path. This approach moves beyond action-local checks to whole-workflow guidance.

In evaluations across the τ²-bench airline, retail, and telecom domains using a GPT-5.4 agent and verifier, PolicyGuide raised the mean Pass^4 score from 0.42 to 0.62. The most significant improvement was observed in the telecom domain, which is the most workflow-structured, jumping from 0.19 to 0.61. The same workflows also transferred effectively to Claude Sonnet 4.6 and Gemini 2.5 Pro agents.

Complementary evaluations highlighted PolicyGuide's robustness: it achieved the lowest observed attack-success rate under adversarial users and demonstrated the strongest procedural compliance in an author-designed workflow-level validation. These results suggest that PolicyGuide offers a promising solution for ensuring policy adherence in customer-service LLM agents.

DomainPass^4 BeforePass^4 After
Airline
Retail
Telecom0.190.61
Mean (all domains)0.420.62
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4