{"ID":2831638,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.07424","arxiv_id":"2512.07424","title":"OnePiece: The Great Route to Generative Recommendation -- A Case Study from Tencent Algorithm Competition","abstract":"In past years, the OpenAI's Scaling-Laws shows the amazing intelligence with the next-token prediction paradigm in neural language modeling, which pointing out a free-lunch way to enhance the model performance by scaling the model parameters. In RecSys, the retrieval stage is also follows a 'next-token prediction' paradigm, to recall the hunderds of items from the global item set, thus the generative recommendation usually refers specifically to the retrieval stage (without Tree-based methods). This raises a philosophical question: without a ground-truth next item, does the generative recommendation also holds a potential scaling law? In retrospect, the generative recommendation has two different technique paradigms: (1) ANN-based framework, utilizing the compressed user embedding to retrieve nearest other items in embedding space, e.g, Kuaiformer. (2) Auto-regressive-based framework, employing the beam search to decode the item from whole space, e.g, OneRec. In this paper, we devise a unified encoder-decoder framework to validate their scaling-laws at same time. Our empirical finding is that both of their losses strictly adhere to power-law Scaling Laws ($R^2$\u003e0.9) within our unified architecture.","short_abstract":"In past years, the OpenAI's Scaling-Laws shows the amazing intelligence with the next-token prediction paradigm in neural language modeling, which pointing out a free-lunch way to enhance the model performance by scaling the model parameters. In RecSys, the retrieval stage is also follows a 'next-token prediction' para...","url_abs":"https://arxiv.org/abs/2512.07424","url_pdf":"https://arxiv.org/pdf/2512.07424v1","authors":"[\"Jiangxia Cao\",\"Shuo Yang\",\"Zijun Wang\",\"Qinghai Tan\"]","published":"2025-12-08T10:56:56Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Language Model\"]","has_code":false}