Artificial Expert Intelligence through PAC-reasoning

TL;DR

This paper introduces Artificial Expert Intelligence (AEI), a framework that combines domain expertise with PAC-reasoning to enable reliable, precise, and adaptable AI systems with theoretical guarantees for complex problem-solving.

Contribution

It proposes a novel PAC-reasoning paradigm for AEI, providing a foundation for error-bounded, inference-time learning with robust theoretical guarantees.

Findings

Provides a framework for decomposing complex problems reliably

Offers mechanisms to control reasoning precision

Establishes theoretical guarantees for AI reasoning

Abstract

Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top human experts. Existing AI systems often excel at predefined tasks but struggle with adaptability and precision in novel problem-solving. To overcome this, AEI introduces a framework for ``Probably Approximately Correct (PAC) Reasoning". This paradigm provides robust theoretical guarantees for reliably decomposing complex problems, with a practical mechanism for controlling reasoning precision. In reference to the division of human thought into System 1 for intuitive thinking and System 2 for reflective reasoning~\citep{tversky1974judgment}, we refer to this new type of reasoning as System 3 for precise reasoning, inspired by the rigor of the scientific method. AEI thus establishes a foundation for error-bounded, inference-time learning.