On physical implementability of reinforcement-learning-driven reasoning

Abstract:In the machine learning community, the reinforcement-learning-driven reasoning process has been intensively studied since around 2025. In this article, we present a negative result on the hardware implementation of this reinforcement-learning-driven reasoning process in a physical neural network model in the presence of a reward external potential energy for a given reward. In this hardware implementation, the existence of a chain of thought in dynamics contradicts the Lyapunov stability of the system.

Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (cs.LG)

arXiv:2610.14131 [cond-mat.dis-nn]

(or arXiv:2610.14131v1 [cond-mat.dis-nn] for this version)

https://doi.org/10.48550/arXiv.2610.14131 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.