Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning

TL;DR

This paper introduces the MGV framework, enhancing reasoning architectures with explicit monitoring inspired by metacognitive theories, aiming to improve the diagnosis and design of language model reasoning systems.

Contribution

It formalizes a new reasoning architecture that incorporates metacognitive monitoring, addressing the prefix dominance trap in language models.

Findings

Provides a detailed vocabulary for diagnosing reasoning failures

Suggests architectural interventions for improved reasoning

Connects reasoning mechanisms to resource-rational analysis

Abstract

Test-time reasoning architectures such as those following the Generate-Verify paradigm, where a model iteratively refines or verifies its own generated outputs, prioritise generation and verification but exclude the monitoring processes that determine when and how reasoning should begin. This omission may contribute to the prefix dominance trap, in which models commit early to suboptimal reasoning paths and seldom recover, yielding roughly 20% accuracy loss. We address this architectural gap by proposing the Monitor-Generate-Verify (MGV) framework, a computational translation of Flavell's and Nelson and Narens' metacognitive theories that preserves their psychological detail. MGV extends the Generate-Verify paradigm by adding explicit monitoring that captures metacognitive experiences (from difficulty assessments to confidence judgements) before generation begins and refines future monitoring through verification feedback. Though we present no empirical validation, MGV provides a vocabulary for diagnosing component-level failures in reasoning systems, suggests specific architectural interventions for future designs, and identifies connections to resource-rational analysis that may ground its mechanisms in normative principles.