Opus: A Prompt Intention Framework for Complex Workflow Generation
Th\'eo Fagnoni, Mahsun Altin, Chia En Chung, Phillip Kingston, Alan Tuning, Dana O. Mohamed, In\`es Adnani

TL;DR
The paper presents the Opus Prompt Intention Framework, an intermediate layer for LLMs that captures user intentions to generate more accurate and logical complex workflows, especially for multi-intent queries.
Contribution
It introduces a novel intermediate intention capture layer that improves the quality and scalability of workflow generation from complex user queries using LLMs.
Findings
Significant improvement in semantic workflow similarity metrics.
Enhanced logical consistency in generated workflows.
Robust performance on synthetic multi-intent query benchmarks.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsScientific Computing and Data Management · Business Process Modeling and Analysis · Distributed and Parallel Computing Systems
