Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering

TL;DR

This paper introduces verifier engineering, a new post-training paradigm for foundation models that uses automated verifiers to enhance supervision, aiming to advance towards Artificial General Intelligence.

Contribution

It proposes a systematic framework of search, verify, and feedback stages, and reviews current research, establishing verifier engineering as a key pathway for future foundation model development.

Findings

Systematic categorization of verifier engineering process

Comprehensive review of state-of-the-art research

Verifier engineering as a pathway to Artificial General Intelligence

Abstract

The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective supervision signals necessary for further enhancing their capabilities. Consequently, there is an urgent need to explore novel supervision signals and technical approaches. In this paper, we propose verifier engineering, a novel post-training paradigm specifically designed for the era of foundation models. The core of verifier engineering involves leveraging a suite of automated verifiers to perform verification tasks and deliver meaningful feedback to foundation models. We systematically categorize the verifier engineering process into three essential stages: search, verify, and feedback, and provide a comprehensive review of state-of-the-art research developments within each stage. We believe that verifier engineering constitutes a fundamental pathway toward achieving Artificial General Intelligence.