Article citationsMore>>

Schick, T., Dwivedi-Yu, J., Dessi, R., Raileanu, R., Lomeli, M., Hambro, E., et al. (2023) Toolformer: Language Models Can Teach Themselves to Use Tools. Advances in Neural Information Processing Systems 36, New Orleans, 10-16 December 2023, 68539-68551. https://doi.org/10.52202/075280-2997

has been cited by the following article:

• TITLE: AI-Based Thinking: Fast and Slow

  AUTHORS: Adnan Agbaria, Yael Dubinsky

  KEYWORDS: AI-Based Thinking, Dual-Process AI Framework, Neuro-Symbolic Orchestration

  JOURNAL NAME: Journal of Computer and Communications, Vol.14 No.6, June 30, 2026

  ABSTRACT: This paper introduces AI-based Thinking, a dual-process framework inspired by Kahneman’s theory of Fast and Slow cognition. We formalize the distinction between intuitive, pattern-driven inference (Fast Thinking) and deliberate, structured reasoning (Slow Thinking) in artificial intelligence systems. We propose a modular architecture that integrates machine learning models with knowledge-based reasoning systems through a meta-cognitive orchestration layer. Unlike traditional AI pipelines, our framework dynamically balances computational efficiency with contextual depth, enabling adaptive reasoning across domains. A case study based on the SmartAI architecture demonstrates the practical implementation of this framework in scene understanding. We further discuss broader implications for medical diagnosis, cybersecurity, and educational AI systems, and identify open challenges in engineering dual-process artificial intelligence.