RecGPT Technical Report
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913968116727808 |
|---|---|
| author | Yi, Chao Chen, Dian Guo, Gaoyang Tang, Jiakai Wu, Jian Yu, Jing Zhang, Mao Dai, Sunhao Chen, Wen Yang, Wenjun Jiang, Yuning Gao, Zhujin Zheng, Bo Li, Chi Wang, Dimin Wang, Dixuan Li, Fan Zhang, Fan Chen, Haibin Liu, Haozhuang Zhu, Jialin Wang, Jiamang Wu, Jiawei Cui, Jin Huang, Ju Zhang, Kai Liu, Kan Tian, Lang Rao, Liang Li, Longbin Zhao, Lulu He, Na Wang, Peiyang Huang, Qiqi Luo, Tao Su, Wenbo He, Xiaoxiao Tong, Xin Chen, Xu Xi, Xunke Li, Yang Wu, Yaxuan Yang, Yeqiu Hu, Yi Song, Yinnan Li, Yuchen Luo, Yujie Yuan, Yujin Yan, Yuliang Wang, Zhengyang Xiao, Zhibo Ma, Zhixin Zhou, Zile Zhang, Ziqi |
| author_facet | Yi, Chao Chen, Dian Guo, Gaoyang Tang, Jiakai Wu, Jian Yu, Jing Zhang, Mao Dai, Sunhao Chen, Wen Yang, Wenjun Jiang, Yuning Gao, Zhujin Zheng, Bo Li, Chi Wang, Dimin Wang, Dixuan Li, Fan Zhang, Fan Chen, Haibin Liu, Haozhuang Zhu, Jialin Wang, Jiamang Wu, Jiawei Cui, Jin Huang, Ju Zhang, Kai Liu, Kan Tian, Lang Rao, Liang Li, Longbin Zhao, Lulu He, Na Wang, Peiyang Huang, Qiqi Luo, Tao Su, Wenbo He, Xiaoxiao Tong, Xin Chen, Xu Xi, Xunke Li, Yang Wu, Yaxuan Yang, Yeqiu Hu, Yi Song, Yinnan Li, Yuchen Luo, Yujie Yuan, Yujin Yan, Yuliang Wang, Zhengyang Xiao, Zhibo Ma, Zhixin Zhou, Zile Zhang, Ziqi |
| contents | Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem.
To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22879 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RecGPT Technical Report Yi, Chao Chen, Dian Guo, Gaoyang Tang, Jiakai Wu, Jian Yu, Jing Zhang, Mao Dai, Sunhao Chen, Wen Yang, Wenjun Jiang, Yuning Gao, Zhujin Zheng, Bo Li, Chi Wang, Dimin Wang, Dixuan Li, Fan Zhang, Fan Chen, Haibin Liu, Haozhuang Zhu, Jialin Wang, Jiamang Wu, Jiawei Cui, Jin Huang, Ju Zhang, Kai Liu, Kan Tian, Lang Rao, Liang Li, Longbin Zhao, Lulu He, Na Wang, Peiyang Huang, Qiqi Luo, Tao Su, Wenbo He, Xiaoxiao Tong, Xin Chen, Xu Xi, Xunke Li, Yang Wu, Yaxuan Yang, Yeqiu Hu, Yi Song, Yinnan Li, Yuchen Luo, Yujie Yuan, Yujin Yan, Yuliang Wang, Zhengyang Xiao, Zhibo Ma, Zhixin Zhou, Zile Zhang, Ziqi Information Retrieval Computation and Language Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem. |
| title | RecGPT Technical Report |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2507.22879 |