CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness

TL;DR

This paper proposes CTM-AI, a blueprint for general AI inspired by consciousness models, integrating foundation models and processors to achieve flexible, adaptive, and multisensory intelligence.

Contribution

It introduces the CTM-AI framework combining a formal consciousness model with foundation models to advance toward general AI capabilities.

Findings

Achieves state-of-the-art accuracy on MUStARD and UR-FUNNY datasets.

Outperforms existing multimodal and multi-agent frameworks.

Improves over baseline on tool-using and agentic tasks.

Abstract

Despite remarkable advances, today's AI systems remain narrow in scope, falling short of the flexible, adaptive, and multisensory intelligence that characterizes human capabilities. This gap has fueled longstanding debates about whether AI might one day achieve human-like generality or even consciousness, and whether theories of consciousness can inspire new architectures for AI. This paper presents an early blueprint for implementing a general AI system, CTM-AI, combining the Conscious Turing Machine (CTM), a formal machine model of consciousness, with today's foundation models. CTM-AI contains an enormous number of powerful processors ranging from specialized experts (e.g., vision-language models and APIs) to unspecialized general-purpose learners poised to develop their own expertise. Crucially, for whatever problem must be dealt with, information from many processors is selected, integrated, and exchanged appropriately to solve the task. CTM-AI achieves state-of-the-art accuracy on MUStARD (72.28) and UR-FUNNY (72.13), outperforming multimodal and multi-agent frameworks. On tool-using and agentic tasks, CTM-AI achieves 10+ points of improvement on StableToolBench and WebArena-Lite. Overall, CTM-AI offers a principled, testable blueprint for general AI inspired by a model of consciousness.