Better AI through Logical Scaffolding
This work addresses the problem of improving AI reliability for software developers, but it is incremental as it builds on prior runtime monitor techniques.
The paper introduces logical scaffolds as a concept to enhance AI software quality, extending existing runtime monitor ideas from perception systems to broader applications like prediction systems and agent behavior models.
We describe the concept of logical scaffolds, which can be used to improve the quality of software that relies on AI components. We explain how some of the existing ideas on runtime monitors for perception systems can be seen as a specific instance of logical scaffolds. Furthermore, we describe how logical scaffolds may be useful for improving AI programs beyond perception systems, to include general prediction systems and agent behavior models.