@inproceedings{agrawal-etal-2026-bpcf,
title = "{BPCF}: A Token-Efficient Process Model Notation for {LLM}-Based {BPMN} Generation",
author = "Agrawal, Ankit and
Wolf, Nicholas and
Geske, Flora",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.235/",
pages = "3932--3944",
ISBN = "979-8-89176-460-6",
abstract = "Generating Business Process Model and Notation (BPMN) process models with LLMs is costly at the serialization layer. Standard XML and JSON formats consume hundreds to thousands of output tokens per model, creating severe latency and cost bottlenecks for interactive modeling assistants. We present BPCF (Business Process Compact Format), a compact, indentation-based notation designed specifically for LLM emission. BPCF-Full is lossless with respect to the structural constructs found in the PMo benchmark. At 221 tokens per model on average, BPCF-Full is roughly half the size of a Mermaid encoding, 8{\texttimes} smaller than verbose JSON representations (PME JSON) and about 29{\texttimes} smaller than BPMN XML. We evaluated nine BPMN representations across five LLMs and found that BPCF is the most token-efficient format by a wide margin, delivering the lowest cost and latency. Although exact accuracy rankings vary across models, BPCF offers a highly viable accuracy-efficiency trade-off for production systems, successfully modeling complex BPMN constructs where other compact formats fail. In the full-expressivity arm, BPCF-Full+Strict scores 0.469/0.472 on GPT-4o/Gemini at 148{--}155 visible output tokens. We publicly release our grammar, a dependency-free parser, and the full evaluation pipeline."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agrawal-etal-2026-bpcf">
<titleInfo>
<title>BPCF: A Token-Efficient Process Model Notation for LLM-Based BPMN Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flora</namePart>
<namePart type="family">Geske</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Generating Business Process Model and Notation (BPMN) process models with LLMs is costly at the serialization layer. Standard XML and JSON formats consume hundreds to thousands of output tokens per model, creating severe latency and cost bottlenecks for interactive modeling assistants. We present BPCF (Business Process Compact Format), a compact, indentation-based notation designed specifically for LLM emission. BPCF-Full is lossless with respect to the structural constructs found in the PMo benchmark. At 221 tokens per model on average, BPCF-Full is roughly half the size of a Mermaid encoding, 8× smaller than verbose JSON representations (PME JSON) and about 29× smaller than BPMN XML. We evaluated nine BPMN representations across five LLMs and found that BPCF is the most token-efficient format by a wide margin, delivering the lowest cost and latency. Although exact accuracy rankings vary across models, BPCF offers a highly viable accuracy-efficiency trade-off for production systems, successfully modeling complex BPMN constructs where other compact formats fail. In the full-expressivity arm, BPCF-Full+Strict scores 0.469/0.472 on GPT-4o/Gemini at 148–155 visible output tokens. We publicly release our grammar, a dependency-free parser, and the full evaluation pipeline.</abstract>
<identifier type="citekey">agrawal-etal-2026-bpcf</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.235/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3932</start>
<end>3944</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BPCF: A Token-Efficient Process Model Notation for LLM-Based BPMN Generation
%A Agrawal, Ankit
%A Wolf, Nicholas
%A Geske, Flora
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F agrawal-etal-2026-bpcf
%X Generating Business Process Model and Notation (BPMN) process models with LLMs is costly at the serialization layer. Standard XML and JSON formats consume hundreds to thousands of output tokens per model, creating severe latency and cost bottlenecks for interactive modeling assistants. We present BPCF (Business Process Compact Format), a compact, indentation-based notation designed specifically for LLM emission. BPCF-Full is lossless with respect to the structural constructs found in the PMo benchmark. At 221 tokens per model on average, BPCF-Full is roughly half the size of a Mermaid encoding, 8× smaller than verbose JSON representations (PME JSON) and about 29× smaller than BPMN XML. We evaluated nine BPMN representations across five LLMs and found that BPCF is the most token-efficient format by a wide margin, delivering the lowest cost and latency. Although exact accuracy rankings vary across models, BPCF offers a highly viable accuracy-efficiency trade-off for production systems, successfully modeling complex BPMN constructs where other compact formats fail. In the full-expressivity arm, BPCF-Full+Strict scores 0.469/0.472 on GPT-4o/Gemini at 148–155 visible output tokens. We publicly release our grammar, a dependency-free parser, and the full evaluation pipeline.
%U https://aclanthology.org/2026.emnlp-industry.235/
%P 3932-3944
Markdown (Informal)
[BPCF: A Token-Efficient Process Model Notation for LLM-Based BPMN Generation](https://aclanthology.org/2026.emnlp-industry.235/) (Agrawal et al., EMNLP 2026)
ACL