On physical implementability of reinforcement-learning-driven reasoning
New in LLM reasoning; no direction yet. LLM reasoning
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 0 of its 11 references that are in the map. First posted on arXiv 9 Oct 2026.
Builds on
0 of 11 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026All On-Board: Fully On-Chip Neuromorphic Q-Learning with Embedded CartPole Simulation
- 2022On the Learning Mechanisms in Physical Reasoning
- 2026Massively Parallel Reinforcement Learning with a Chaotic Reconfigurable Clockless Chip
- 2015On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
- 2025Reasoning in Neurosymbolic AI
- 2024Neural Reward Machines
- 2025Fully Learnable Neural Reward Machines
- 2024Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks