CTM-AI: A Blueprint for General AI Inspired by Consciousness

ICLR 2026 Conference Submission14721 Authors

Keywords: conscious turing machine, multimodal machine learning

Abstract: Despite remarkable advances, today's AI systems remain narrow in scope, falling short of the flexible, adaptive, and multisensory intelligence that characterizes humans. This gap has fueled longstanding debates about whether AI might one day achieve human-like generality or even consciousness, and whether principles of consciousness can inspire new architectures for general AI. This paper presents an early blueprint for implementing a general AI system based on the Conscious Turing Machine (CTM), a formal machine model of consciousness. The CTM has an enormous number of powerful processors ranging from specialized experts (e.g., vision–language models, search engines, APIs) to unspecialized general-purpose learners poised to develop their own expertise. Crucially, for whatever problem must be dealt with, the system need not know in advance which processors hold the relevant expertise; instead, multimodal machine learning methods enable the system to select, integrate, and fuse information across processors. We extend the CTM into a practical framework, the CTM-AI, and demonstrate its utility on diverse tasks including multimodal perception, tool learning with multiple APIs, and multi-turn web agent tasks. Together, this work offers a principled and testable blueprint for general AI inspired by computational models of consciousness.

Primary Area: applications to neuroscience & cognitive science

Submission Number: 14721