{"ID":2840994,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.12597","arxiv_id":"2511.12597","title":"MindRec: A Diffusion-driven Coarse-to-Fine Paradigm for Generative Recommendation","abstract":"Recent advancements in large language model-based recommendation systems often represent items as text or semantic IDs and generate recommendations in an auto-regressive manner. However, due to the left-to-right greedy decoding strategy and the unidirectional logical flow, such methods often fail to produce globally optimal recommendations. In contrast, human reasoning does not follow a rigid left-to-right sequence. Instead, it often begins with keywords or intuitive insights, which are then refined and expanded. Inspired by this fact, we propose MindRec, a diffusion-driven coarse-to-fine generative paradigm that emulates human thought processes. Built upon a diffusion language model, MindRec departs from auto-regressive generation by leveraging a masked diffusion process to reconstruct items in a flexible, non-sequential manner. Particularly, our method first generates key tokens that reflect user preferences, and then expands them into the complete item, enabling adaptive and human-like generation. To further emulate the structured nature of human decision-making, we organize items into a hierarchical category tree. This structure guides the model to first produce the coarse-grained category and then progressively refine its selection through finer-grained subcategories before generating the specific item. To mitigate the local optimum problem inherent in greedy decoding, we design a novel beam search algorithm, Diffusion Beam Search, tailored for our mind-inspired generation paradigm. Experimental results demonstrate that MindRec yields a 9.5\\% average improvement in top-1 accuracy over state-of-the-art methods, highlighting its potential to enhance recommendation performance. The implementation is available via https://github.com/Mr-Peach0301/MindRec.","short_abstract":"Recent advancements in large language model-based recommendation systems often represent items as text or semantic IDs and generate recommendations in an auto-regressive manner. However, due to the left-to-right greedy decoding strategy and the unidirectional logical flow, such methods often fail to produce globally op...","url_abs":"https://arxiv.org/abs/2511.12597","url_pdf":"https://arxiv.org/pdf/2511.12597v2","authors":"[\"Mengyao Gao\",\"Chongming Gao\",\"Haoyan Liu\",\"Qingpeng Cai\",\"Peng Jiang\",\"Jiajia Chen\",\"Shuai Yuan\",\"Xiangnan He\"]","published":"2025-11-16T13:42:59Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Diffusion Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":607018,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2840994,"paper_url":"https://arxiv.org/abs/2511.12597","paper_title":"MindRec: A Diffusion-driven Coarse-to-Fine Paradigm for Generative Recommendation","repo_url":"https://github.com/Mr-Peach0301/MindRec","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}