A Composable Just-In-Time Programming Framework with LLMs and FBP
Andy Vidan, Lars H. Fiedler

TL;DR
This paper presents a novel computing framework that combines Flow-Based Programming and Large Language Models to enable real-time, user-friendly code generation and automation, enhancing flexibility and accessibility in software development.
Contribution
It introduces a new JITP framework integrating LLMs with FBP, allowing dynamic, on-demand code generation for users without extensive programming skills.
Findings
Effective real-time code generation demonstrated
Enhanced automation in data workflows shown
Improved user participation in programming processes
Abstract
This paper introduces a computing framework that combines Flow-Based Programming (FBP) and Large Language Models (LLMs) to enable Just-In-Time Programming (JITP). JITP empowers users, regardless of their programming expertise, to actively participate in the development and automation process by leveraging their task-time algorithmic insights. By seamlessly integrating LLMs into the FBP workflow, the framework allows users to request and generate code in real-time, enabling dynamic code execution within a flow-based program. The paper explores the motivations, principles, and benefits of JITP, showcasing its potential in automating tasks, orchestrating data workflows, and accelerating software development. Through a fully implemented JITP framework using the Composable platform, we explore several examples and use cases to illustrate the benefits of the framework in data engineering,…
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
TopicsContext-Aware Activity Recognition Systems · Scientific Computing and Data Management · Software System Performance and Reliability
