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

Nick Oh, Fernand Gobet

Keywords: large reasoning model, self-refinement, self-verification, metacognition, resource-rational, metareasoning, metalearning

TL;DR: We formalise classical metacognitive theories (Flavell, Nelson & Narens) into computational frameworks and introduce Monitor-Generate-Verify as a theoretical approach to reasoning.

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 and suggests specific architectural interventions for future designs.

Submission Number: 159