{"ID":2864596,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23140","arxiv_id":"2509.23140","title":"Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning","abstract":"Recent advancements have endowed Large Language Models (LLMs) with impressive general reasoning capabilities, yet they often struggle with personalization reasoning - the crucial ability to analyze user history, infer unique preferences, and generate tailored responses. To address this limitation, we introduce TagPR, a novel training framework that significantly enhances an LLM's intrinsic capacity for personalization reasoning through a tagging the thought approach. Our method first develops a data-driven pipeline to automatically generate and semantically label reasoning chains, creating a structured dataset that fosters interpretable reasoning. We then propose a synergistic training strategy that begins with Supervised Fine-Tuning (SFT) on this tagged data to establish foundational reasoning patterns, followed by a multi-stage reinforcement learning (RL) process. This RL phase is guided by a unique composite reward signal, which integrates tag-based constraints and a novel Personalization Reward Model with User Embeddings (PRMU) to achieve fine-grained alignment with user-specific logic. Extensive experiments on the public LaMP benchmark and a self-constructed dataset demonstrate that our approach achieves state-of-the-art results, delivering an average improvement of 32.65% over the base model across all tasks. Our work validates that structured, interpretable reasoning is a highly effective pathway to unlocking genuine personalization capabilities in LLMs.","short_abstract":"Recent advancements have endowed Large Language Models (LLMs) with impressive general reasoning capabilities, yet they often struggle with personalization reasoning - the crucial ability to analyze user history, infer unique preferences, and generate tailored responses. To address this limitation, we introduce TagPR, a...","url_abs":"https://arxiv.org/abs/2509.23140","url_pdf":"https://arxiv.org/pdf/2509.23140v1","authors":"[\"Song Jin\",\"Juntian Zhang\",\"Yong Liu\",\"Xun Zhang\",\"Yufei Zhang\",\"Fei Jiang\",\"Guojun Yin\",\"Wei Lin\",\"Rui Yan\"]","published":"2025-09-27T06:03:44Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}