Author name: Pawel Kaplanski (Kaplanski AI Lab)

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

Pawel Kaplanski (Kaplanski AI Lab) / May 6, 2026

arXiv:2605.02236v2 Announce Type: replace
Abstract: Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to move a settled loop somewhere else, and whether th…

cs.AI, cs.CL, cs.LG

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

Pawel Kaplanski (Kaplanski AI Lab) / May 5, 2026

arXiv:2605.02236v1 Announce Type: cross
Abstract: Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to move a settled loop somewhere else, and whether that…