preprint
<title>Abstract</title> Computational problem-solving often lacks effective verification processes, which introduces potential inaccuracies in problem-solving approaches. This research examines meta-cognitive methods for systematic problem-solving, emphasizing constraint realization, invariant property analysis, and solution verification. Drawing from recent advances in AI metacognition and cognitive problem-solving frameworks, we demonstrate the importance of systematic problem-solving protocols in eliminating cognitive biases and unverified claims to ensure correct solutions. The study introduces a structured verification model that integrates constraint realization, invariant property analysis, and systematic reasoning to enhance AI decision-making processes and reliability. Our experimental evaluation across leading AI models demonstrates significant variations in metacognitive problem-solving capabilities, with most models showing substantial improvement when guided by structured metacognitive prompts.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.21203/rs.3.rs-6185693/v1
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
