Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.11288 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909746303336448 |
|---|---|
| author | Fagnoni, Théo Altin, Mahsun Chung, Chia En Kingston, Phillip Tuning, Alan Mohamed, Dana O. Adnani, Inès |
| author_facet | Fagnoni, Théo Altin, Mahsun Chung, Chia En Kingston, Phillip Tuning, Alan Mohamed, Dana O. Adnani, Inès |
| contents | This paper introduces the Opus Prompt Intention Framework, designed to improve complex Workflow Generation with instruction-tuned Large Language Models (LLMs). We propose an intermediate Intention Capture layer between user queries and Workflow Generation, implementing the Opus Workflow Intention Framework, which consists of extracting Workflow Signals from user queries, interpreting them into structured Workflow Intention objects, and generating Workflows based on these Intentions. Our results show that this layer enables LLMs to produce logical and meaningful outputs that scale reliably as query complexity increases. On a synthetic benchmark of 1,000 multi-intent query-Workflow(s) pairs, applying the Opus Prompt Intention Framework to Workflow Generation yields consistent improvements in semantic Workflow similarity metrics. In this paper, we introduce the Opus Prompt Intention Framework by applying the concepts of Workflow Signal and Workflow Intention to LLM-driven Workflow Generation. We present a reproducible, customizable LLM-based Intention Capture system to extract Workflow Signals and Workflow Intentions from user queries. Finally, we provide empirical evidence that the proposed system significantly improves Workflow Generation quality compared to direct generation from user queries, particularly in cases of Mixed Intention Elicitation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11288 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Opus: A Prompt Intention Framework for Complex Workflow Generation Fagnoni, Théo Altin, Mahsun Chung, Chia En Kingston, Phillip Tuning, Alan Mohamed, Dana O. Adnani, Inès Artificial Intelligence This paper introduces the Opus Prompt Intention Framework, designed to improve complex Workflow Generation with instruction-tuned Large Language Models (LLMs). We propose an intermediate Intention Capture layer between user queries and Workflow Generation, implementing the Opus Workflow Intention Framework, which consists of extracting Workflow Signals from user queries, interpreting them into structured Workflow Intention objects, and generating Workflows based on these Intentions. Our results show that this layer enables LLMs to produce logical and meaningful outputs that scale reliably as query complexity increases. On a synthetic benchmark of 1,000 multi-intent query-Workflow(s) pairs, applying the Opus Prompt Intention Framework to Workflow Generation yields consistent improvements in semantic Workflow similarity metrics. In this paper, we introduce the Opus Prompt Intention Framework by applying the concepts of Workflow Signal and Workflow Intention to LLM-driven Workflow Generation. We present a reproducible, customizable LLM-based Intention Capture system to extract Workflow Signals and Workflow Intentions from user queries. Finally, we provide empirical evidence that the proposed system significantly improves Workflow Generation quality compared to direct generation from user queries, particularly in cases of Mixed Intention Elicitation. |
| title | Opus: A Prompt Intention Framework for Complex Workflow Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.11288 |