CTM-AI: Evolving Multi-Agent Intelligence Inspired by a Model of Consciousness

Abstract

Despite remarkable advances, today's AI systems remain narrow in scope, falling short of the adaptive and continual intelligence that characterizes human capabilities. This gap has fueled longstanding debates about whether AI might one day achieve human-like generality or even consciousness. Flipping the debate, we present a concrete blueprint for a multi-agent AI system inspired by a formal machine model of consciousness called the Conscious Turing Machine (CTM). Together, CTM-AI contains a large collection of powerful processors ranging from specialized experts (e.g., language models, multimodal models, tools, 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 competitively selected, integrated, and exchanged appropriately to solve the task. Feedback mechanisms in CTM-AI enable the system to iteratively evolve its internal connections and communication. 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 and testable multi-agent AI system inspired by a model of consciousness. The code is available at https://github.com/consciousness-lab/ctm-ai.

Inferring Affective Consciousness in an Artificial Agent: A Case Study
Mark Solms, St John Grimbly, Bruce Bassett +7
arXiv3 Sep 2026PreprintCC BY 4.0Full textNeurosciencearXiv
ADMET-EvO: a self-evolving scientific agent for sustained research across heterogeneous tasks
Yiling Zhou, Yilin Wang, Jianmin Wang +8
arXiv10 Sep 2026PreprintCC BY 4.0Full textBioinformatics & computational biologyarXiv
Learning from Expert-Corrected Misdiagnoses: A Self-Evolving Consultation Agent for Traditional Chinese Medicine after Failed Treatment
Ye Wang, Zhikang Lin, Jia Liu +2
arXiv9 Oct 2026PreprintarXiv licenceFull textGeneral biologyarXiv
Navigating the rapidly evolving landscape of sequencing-based spatial transcriptomics technologies: a comprehensive multi-platform benchmark
J. Mortier, I. Scheyltjens, E. Kuznecova +11
bioRxiv15 Oct 2026PreprintCC BYFull textGenetics & genomicsbioRxiv
If the brain were so simple: Information-based drivers of intelligence and their interaction through an n-body-inspired framework
Brett J. Kagan, Johnson Zhou, Forough Habibollahi +1
arXiv8 Oct 2026PreprintCC BY-NC-ND 4.0Full textNeuroscience General mathematicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{yu2026ctmai,
  title = {{CTM-AI: Evolving Multi-Agent Intelligence Inspired by a Model of Consciousness}},
  author = {Haofei Yu and Yining Zhao and Lenore Blum and Manuel Blum and Paul Pu Liang},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2605.04097},
  eprint = {2605.04097},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.04097},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - CTM-AI: Evolving Multi-Agent Intelligence Inspired by a Model of Consciousness
AU  - Haofei Yu
AU  - Yining Zhao
AU  - Lenore Blum
AU  - Manuel Blum
AU  - Paul Pu Liang
PY  - 2026
DA  - 2026/11/01
PB  - arXiv
DO  - 10.48550/arxiv.2605.04097
UR  - https://arxiv.org/abs/2605.04097
AB  - Despite remarkable advances, today's AI systems remain narrow in scope, falling short of the adaptive and continual intelligence that characterizes human capabilities. This gap has fueled longstanding debates about whether AI might one day achieve human-like generality or even consciousness. Flipping the debate, we present a concrete blueprint for a multi-agent AI system inspired by a formal machine model of consciousness called the Conscious Turing Machine (CTM). Together, CTM-AI contains a large collection of powerful processors ranging from specialized experts (e.g., language models, multimodal models, tools, 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 competitively selected, integrated, and exchanged appropriately to solve the task. Feedback mechanisms in CTM-AI enable the system to iteratively evolve its internal connections and communication. 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 and testable multi-agent AI system inspired by a model of consciousness. The code is available at https://github.com/consciousness-lab/ctm-ai.
ER  -

Abstract

Related

Cite