Xiaoyu Kong
Xiaoyu Kong has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- An Zhang
University of Science and Technology of China, Hefei, China
1 shared publication - Bin Liu
Taobao & Tmall Group of Alibaba, Beijing, China
1 shared publication - Bo Zheng
Alibaba Group, Hangzhou, China
1 shared publication - Chunxu Shen
Tencent Inc., Shenzhen, China
1 shared publication - Han Zhu
Taobao & Tmall Group of Alibaba, Beijing, China
1 shared publication - Jian Xu
Alibaba Group, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8319-8327
Large Language Model as Universal Retriever in Industrial-Scale Recommender System
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8319-8327
Open AccessLarge Language Model as Universal Retriever in Industrial-Scale Recommender System
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1638-1649
Reasoning over Semantic IDs Enhances Generative Recommendation
Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generation over a unified token space comprising language tokens and itemic identifiers, where each item is represented by a compact sequence of discrete tokens, namely Semantic IDs (SIDs). This SID-based formulation enables efficient decoding over large-scale item corpora and provides a natural interface for LLM-based recommenders to leverage rich world knowledge. Meanwhile, breakthroughs in LLM reasoning motivate reasoning-enhanced recommendation, yet effective reasoning over SIDs remains underexplored and challenging. Itemic tokens are not natively meaningful to LLMs; moreover, recommendation-oriented SID reasoning is hard to evaluate, making high-quality supervision scarce. To address these challenges, we propose SIDReasoner, a two-stage framework that elicits reasoning over SIDs by strengthening SID–language alignment to unlock transferable LLM reasoning, rather than relying on large amounts of recommendationspecific reasoning traces. Concretely, SIDReasoner first enhances SID-language alignment via multi-task training on an enriched SID-centered corpus synthesized by a stronger teacher model, grounding itemic tokens in diverse semantic and behavioral contexts. Building on this enhanced alignment, SIDReasoner further improves recommendation reasoning through outcome-driven reinforced optimization, which guides the model toward effective reasoning trajectories without requiring explicit reasoning annotations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our reasoning-augmented SID-based generative recommendation. Beyond accuracy, the results highlight the broader potential of large reasoning models for generative recommendation, including improved interpretability and cross-domain generalization. Our codes are available at https://github.com/HappyPointer/SIDReasoner.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1638-1649
Open AccessReasoning over Semantic IDs Enhances Generative Recommendation
Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generation over a unified token space comprising language tokens and itemic identifiers, where each item is represented by a compact sequence of discrete tokens, namely Semantic IDs (SIDs). This SID-based formulation enables efficient decoding over large-scale item corpora and provides a natural interface for LLM-based recommenders to leverage rich world knowledge. Meanwhile, breakthroughs in LLM reasoning motivate reasoning-enhanced recommendation, yet effective reasoning over SIDs remains underexplored and challenging. Itemic tokens are not natively meaningful to LLMs; moreover, recommendation-oriented SID reasoning is hard to evaluate, making high-quality supervision scarce. To address these challenges, we propose SIDReasoner, a two-stage framework that elicits reasoning over SIDs by strengthening SID–language alignment to unlock transferable LLM reasoning, rather than relying on large amounts of recommendationspecific reasoning traces. Concretely, SIDReasoner first enhances SID-language alignment via multi-task training on an enriched SID-centered corpus synthesized by a stronger teacher model, grounding itemic tokens in diverse semantic and behavioral contexts. Building on this enhanced alignment, SIDReasoner further improves recommendation reasoning through outcome-driven reinforced optimization, which guides the model toward effective reasoning trajectories without requiring explicit reasoning annotations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our reasoning-augmented SID-based generative recommendation. Beyond accuracy, the results highlight the broader potential of large reasoning models for generative recommendation, including improved interpretability and cross-domain generalization. Our codes are available at https://github.com/HappyPointer/SIDReasoner.