{"ID":2864948,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21777","arxiv_id":"2509.21777","title":"SynerGen: Contextualized Generative Recommender for Unified Search and Recommendation","abstract":"The dominant retrieve-then-rank pipeline in large-scale recommender systems suffers from mis-calibration and engineering overhead due to its architectural split and differing optimization objectives. While recent generative sequence models have shown promise in unifying retrieval and ranking by auto-regressively generating ranked items, existing solutions typically address either personalized search or query-free recommendation, often exhibiting performance trade-offs when attempting to unify both. We introduce \\textit{SynerGen}, a novel generative recommender model that bridges this critical gap by providing a single generative backbone for both personalized search and recommendation, while simultaneously excelling at retrieval and ranking tasks. Trained on behavioral sequences, our decoder-only Transformer leverages joint optimization with InfoNCE for retrieval and a hybrid pointwise-pairwise loss for ranking, allowing semantic signals from search to improve recommendation and vice versa. We also propose a novel time-aware rotary positional embedding to effectively incorporate time information into the attention mechanism. \\textit{SynerGen} achieves significant improvements on widely adopted recommendation and search benchmarks compared to strong generative recommender and joint search and recommendation baselines. This work demonstrates the viability of a single generative foundation model for industrial-scale unified information access.","short_abstract":"The dominant retrieve-then-rank pipeline in large-scale recommender systems suffers from mis-calibration and engineering overhead due to its architectural split and differing optimization objectives. While recent generative sequence models have shown promise in unifying retrieval and ranking by auto-regressively genera...","url_abs":"https://arxiv.org/abs/2509.21777","url_pdf":"https://arxiv.org/pdf/2509.21777v1","authors":"[\"Vianne R. Gao\",\"Chen Xue\",\"Marc Versage\",\"Xie Zhou\",\"Zhongruo Wang\",\"Chao Li\",\"Yeon Seonwoo\",\"Nan Chen\",\"Zhen Ge\",\"Gourab Kundu\",\"Weiqi Zhang\",\"Tian Wang\",\"Qingjun Cui\",\"Trishul Chilimbi\"]","published":"2025-09-26T02:27:04Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Transformer\"]","has_code":false}