Stanford and Tsinghua paper finds dopamine-like reward neurons naturally evolved in LLMs

chrismattmann · x · 2026-09-22

A paper from Stanford and Tsinghua reportedly shows LLMs have spontaneously evolved a biological-style reward subsystem: a highly sparse subset (under 1%) of neurons does the heavy lifting for self-correction. 'Value neurons' function like the prefrontal cortex, signaling expected state value and confidence before the next token is generated, while others map to dopamine neurons. The researchers stress this was not programmed but emerged naturally.

Original post →

More from Research

Research channel →