Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

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

Seongjae Kang, Taehyung Yu, Sung Ju Hwang

Published

Aug 20, 2026

Citations

0

Trust level

Low

Usefulness score

25/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 20, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Long Horizon Math

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

The available metadata is too thin to trust this as a primary source.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
25/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure. Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior. PolicyGuide instead compiles each domain policy into a workflow graph and invokes a proactive verifier at user-turn boundaries. From persisted graph state, the verifier reconciles open requests and returns step-specific remediation along a policy-compliant path. Across the $τ^2$-bench airline, retail, and telecom domains with a GPT-5.4 agent and verifier, PolicyGuide raises mean $\mathrm{Pass}^4$ from $0.42$ to $0.62$, with the largest gain on telecom ($0.19$ to $0.61$), the most workflow-structured domain. The same workflows transfer to Claude Sonnet 4.6 and Gemini 2.5 Pro agents. Complementary evaluations find the lowest observed attack-success rate under adversarial users and the strongest procedural compliance in an author-designed workflow-level validation.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Customer-service LLM agents must follow organizational policy when acting on a user's behalf."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Customer-service LLM agents must follow organizational policy when acting on a user's behalf."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Customer-service LLM agents must follow organizational policy when acting on a user's behalf."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Customer-service LLM agents must follow organizational policy when acting on a user's behalf."

Reported Metrics

partial

Success rate, Jailbreak success rate

Useful for evaluation criteria comparison.

"Complementary evaluations find the lowest observed attack-success rate under adversarial users and the strongest procedural compliance in an author-designed workflow-level validation."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

success ratejailbreak success rate
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Math
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Customer-service LLM agents must follow organizational policy when acting on a user's behalf.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Customer-service LLM agents must follow organizational policy when acting on a user's behalf.
  • Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation.
  • Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Long-horizon tasks) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Customer-service LLM agents must follow organizational policy when acting on a user's behalf.
  • Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure.
  • Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior.

Why it matters for eval

  • Customer-service LLM agents must follow organizational policy when acting on a user's behalf.
  • Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: success rate, jailbreak success rate