looped-language-models

Tag

Cards List
#looped-language-models

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary

arXiv cs.LG · 2026-07-22 Cached

This paper investigates whether a frozen looped transformer can read its own computation quality (pre-answer prediction reaching AUROC 0.797) and whether external interventions can improve outcomes, finding that no tested frozen intervention produces a validated capability gain, a property termed operational proto-introspection.

0 favorites 0 likes
← Back to home

Submit Feedback