Personalized Reasoning: Just-in-time Personalization and Why LLMs Fail at It

ICLR 2026 Conference Submission22039 Authors

Keywords: Interactive Personalization, Test-time Reasoning, Information Seeking, Preference Alignment

TL;DR: We introduce the task of Personalized Reasoning, in which LLMs need to reason about missing user preferences, strategically elicit preference values, then adapt their reasoning processes and responses accordingly.

Abstract: Current large language model (LLM) development treats task-solving and preference-alignment as separate challenges, optimizing first for objective correctness, then for alignment to aggregated human preferences. This paradigm fails in human-facing applications where solving a problem correctly is insufficient if the response mismatches the user’s needs. This challenge intensifies in just-in-time scenarios where no prior user interaction history exists due to cold-start conditions or privacy constraints. LLMs need to identify what they don’t know about user preferences, strategically elicit preference values through questioning, then adapt their reasoning processes and responses accordingly—a complicated chain of cognitive processes which we term personalized reasoning. We introduce PrefDisco, an evaluation methodology that transforms static benchmarks into interactive personalization tasks using psychologically-grounded personas with sparse preferences. Our framework creates scenarios where identical questions require different reasoning chains depending on user context, as optimal explanation approaches vary by individual expertise and preferences while maintaining factual accuracy. Evaluation of 21 frontier models across 10 tasks reveals 29.0% of naive personalization attempts produce worse preference alignment than generic responses, yet generic responses also fail to serve individual user needs effectively. These findings suggest personalized reasoning requires dedicated development rather than emerging naturally from general language understanding improvements. PrefDisco establishes personalized reasoning as a measurable research frontier and reveals fundamental limitations in current LLMs’ interactive capabilities, providing a foundation for developing systems that can adapt to individual users in education, healthcare, and technical domains where personalization is critical.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 22039