An Infrastructure Software Perspective Toward Computation Offloading between Executable Specifications and Foundation Models
Dezhi Ran, Mengzhou Wu, Yuan Cao, Assaf Marron, David Harel, Tao, Xie

TL;DR
This paper proposes a framework for computation offloading between Foundation Models and executable specifications, aiming to enhance hybrid software system efficiency and reliability through strategic task distribution.
Contribution
It introduces a novel infrastructure framework for offloading tasks between FMs and symbolic programs, addressing key challenges like semantic gaps and scalability.
Findings
Framework design for task decomposition and resource allocation
Identification of technical challenges such as semantic gaps and reliability
Potential for more efficient and reliable hybrid software systems
Abstract
Foundation Models (FMs) have become essential components in modern software systems, excelling in tasks such as pattern recognition and unstructured data processing. However, their capabilities are complemented by the precision, verifiability, and deterministic nature of executable specifications, such as symbolic programs. This paper explores a new perspective on computation offloading, proposing a framework that strategically distributes computational tasks between FMs and executable specifications based on their respective strengths. We discuss the potential design of an infrastructure software framework to enable this offloading, focusing on key mechanisms such as task decomposition, resource allocation, and adaptive optimization. Furthermore, we identify critical technical challenges, including semantic-gap resolution, reliability, and scalability, that must be addressed to realize…
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
TopicsSoftware System Performance and Reliability · Scientific Computing and Data Management · Model-Driven Software Engineering Techniques
