Prompt Orchestration Markup Language

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yuge, Chen, Nan, Xu, Jiahang, Yang, Yuqing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911111206404096
author Zhang, Yuge
Chen, Nan
Xu, Jiahang
Yang, Yuqing
author_facet Zhang, Yuge
Chen, Nan
Xu, Jiahang
Yang, Yuqing
contents Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to decouple content from presentation, reducing formatting sensitivity. It includes templating for dynamic prompts and a comprehensive developer toolkit (IDE support, SDKs) to improve version control and collaboration. We validate POML through two case studies demonstrating its impact on complex application integration (PomLink) and accuracy performance (TableQA), as well as a user study assessing its effectiveness in real-world development scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt Orchestration Markup Language
Zhang, Yuge
Chen, Nan
Xu, Jiahang
Yang, Yuqing
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Programming Languages
Large Language Models (LLMs) require sophisticated prompting, yet current practices face challenges in structure, data integration, format sensitivity, and tooling. Existing methods lack comprehensive solutions for organizing complex prompts involving diverse data types (documents, tables, images) or managing presentation variations systematically. To address these gaps, we introduce POML (Prompt Orchestration Markup Language). POML employs component-based markup for logical structure (roles, tasks, examples), specialized tags for seamless data integration, and a CSS-like styling system to decouple content from presentation, reducing formatting sensitivity. It includes templating for dynamic prompts and a comprehensive developer toolkit (IDE support, SDKs) to improve version control and collaboration. We validate POML through two case studies demonstrating its impact on complex application integration (PomLink) and accuracy performance (TableQA), as well as a user study assessing its effectiveness in real-world development scenarios.
title Prompt Orchestration Markup Language
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
Programming Languages
url https://arxiv.org/abs/2508.13948