Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs

Anand Iyer, Bhanu Khetharpal, Srinivas Upadhya, Ramkumar Rajagopal

Published

Aug 31, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

35% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 31, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

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

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
0/100
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

This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers. Each target is a directed acyclic graph (DAG) of conditional actions with parallel branches, hit-first fallback chains, and per-branch Boolean predicates, encoded in the JSON dialect of a commercial routing platform. We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models. Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the number of interdependent nodes emitted in one pass grows. We therefore move combinatorial graph construction from the model into a deterministic compiler driven by a compact intermediate representation, with a learned registry-selection front end that focuses generation on relevant vocabulary. Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt. On GPT-5.3-chat, the method improves judge validity by 24 percentage points and achieves statistical equivalence to a reasoning model's out-of-the-box quality, although an approximately 8-point frontier gap remains. We also present a deployment path and transferable lessons for structured-generation applications.

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.

"This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers."

Quality Controls

missing

Not reported

No explicit QC controls found.

"This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers."

Reported Metrics

partial

Accuracy, Exact match

Useful for evaluation criteria comparison.

"Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the number of interdependent nodes emitted in one pass grows."

Benchmarks and datasets

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

Reported metrics

accuracyexact match
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers.

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

Key takeaways

  • This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers.
  • Each target is a directed acyclic graph (DAG) of conditional actions with parallel branches, hit-first fallback chains, and per-branch Boolean predicates, encoded in the JSON dialect of a commercial routing platform.
  • We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) 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

Accuracy

Contribution summary

  • We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models.
  • Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the…
  • Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt.

Why it matters for eval

  • Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the…
  • Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt.

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: accuracy, exact match