EPISODE · Aug 21, 2025 · 23 MIN
Prompt Orchestration Markup Language
from Daily Paper Cast · host Jingwen Liang, Gengyu Wang
🤗 Upvotes: 24 | cs.HC, cs.AI, cs.CL, cs.PL Authors: Yuge Zhang, Nan Chen, Jiahang Xu, Yuqing Yang Title: Prompt Orchestration Markup Language Arxiv: http://arxiv.org/abs/2508.13948v1 Abstract: 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.
What this episode covers
🤗 Upvotes: 24 | cs.HC, cs.AI, cs.CL, cs.PL Authors: Yuge Zhang, Nan Chen, Jiahang Xu, Yuqing Yang Title: Prompt Orchestration Markup Language Arxiv: http://arxiv.org/abs/2508.13948v1 Abstract: 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.
NOW PLAYING
Prompt Orchestration Markup Language
No transcript for this episode yet
Similar Episodes
No similar episodes found.