Test-Time Personalization: A Diagnostic Framework and Probabilistic Fix for Scaling Failures

arXiv:2605.10991v1 Announce Type: cross Abstract: Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process. In this work, we study Test-Time Personalization (TTP) along an unexplored axis: scaling inference-time computation by sampling N candidates from a personalized policy model and selecting the best with a personalized reward model. We prove that oracle selection yields expected utility growing lo