◍wovepaper
SearchResearchersInstitutions
Sign in
institution

Kai Research (United States)

United States

1 paper here
fields
  • cs.AI1
ROR 015nmh932OpenAlex

affiliations via OpenAlex

researchers with a paper here
  • Pawel Kaplanski1 · h 7
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Pawel Kaplanski

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 e…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.