Xiaopeng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xiaopeng Li has a total of 112 co-authors. Here are the top co-authors by number of shared publications:
- Xiangyu Zhao
City University of Hong Kong, Kowloon Tong, Hong Kong
16 shared publications - Pengyue Jia
City University of Hong Kong, Hong Kong, China
11 shared publications - Yichao Wang
Huawei Technologies Ltd., Shenzhen, China
11 shared publications - Huifeng Guo
Huawei Technologies, Shenzhen, China
10 shared publications - Ruiming Tang
Kuaishou Technology, Beijing, China
10 shared publications - Wenlin Zhang
City University of Hong Kong, Hong Kong, China
6 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1801-1812
GloRank: Generative Reranking for Deep Recommender Systems via Global Identifier Generation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1801-1812
Open AccessGloRank: Generative Reranking for Deep Recommender Systems via Global Identifier Generation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6688-6699
When Hard Negatives Hurt: Bridging the Generative Discriminative Gap in Hard Negative Synthesis for Retrieval
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 6688-6699
Open AccessWhen Hard Negatives Hurt: Bridging the Generative Discriminative Gap in Hard Negative Synthesis for Retrieval
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13343-13346
Tutorial on Generative Recommendation: Foundations and Frontiers
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13343-13346
Open AccessTutorial on Generative Recommendation: Foundations and Frontiers
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5336-5339
Bridging Personalization and AI: From RAG to Agent
Personalization is becoming a core capability of modern AI systems. It enables systems to adapt their responses and behaviors according to individual users' preferences, contexts, and goals. Recent research has focused on Retrieval-Augmented Generation (RAG) and its development toward more advanced agent-based frameworks to improve user satisfaction in personalized settings. In this tutorial, we provide a systematic overview of how personalization can be incorporated into the three main stages of RAG: pre-retrieval, retrieval, and generation. We then extend the discussion to personalized LLM-based agents, which build on RAG by adding agent capabilities such as user understanding, personalized planning and execution, and adaptive response generation. For both RAG-based and agent-based approaches, we present clear definitions, review recent research, and summarize commonly used datasets and evaluation metrics. We also discuss key challenges, current limitations, and potential future research directions. An updated list of related papers and resources is available at our GitHub repository. https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent. Further updates for this tutorial will be uploaded on the homepage. https://applied-machine-learning-lab.github.io/SIGIR2026_PRAG_Tutorial.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5336-5339
Open AccessBridging Personalization and AI: From RAG to Agent
Personalization is becoming a core capability of modern AI systems. It enables systems to adapt their responses and behaviors according to individual users' preferences, contexts, and goals. Recent research has focused on Retrieval-Augmented Generation (RAG) and its development toward more advanced agent-based frameworks to improve user satisfaction in personalized settings. In this tutorial, we provide a systematic overview of how personalization can be incorporated into the three main stages of RAG: pre-retrieval, retrieval, and generation. We then extend the discussion to personalized LLM-based agents, which build on RAG by adding agent capabilities such as user understanding, personalized planning and execution, and adaptive response generation. For both RAG-based and agent-based approaches, we present clear definitions, review recent research, and summarize commonly used datasets and evaluation metrics. We also discuss key challenges, current limitations, and potential future research directions. An updated list of related papers and resources is available at our GitHub repository. https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent. Further updates for this tutorial will be uploaded on the homepage. https://applied-machine-learning-lab.github.io/SIGIR2026_PRAG_Tutorial.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3284-3291
Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3284-3291
Open AccessPersonalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery
- Top Cited PapersOpen Access
- 11 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (4) , 1-39
A Survey of Personalization: From RAG to Agent
Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented Generation (RAG) frameworks and their evolution into more advanced agent-based architectures within personalized settings to enhance user satisfaction. Building on this foundation, this survey systematically examines personalization across the three core stages of RAG: pre-retrieval, retrieval, and generation. Beyond RAG, we further extend its capabilities into the realm of Personalized LLM-based Agents, which enhance traditional RAG systems with agentic functionalities, including user understanding, personalized planning and execution, and dynamic generation. For both personalization in RAG and agent-based personalization, we provide formal definitions, conduct a comprehensive review of recent literature, and summarize key datasets and evaluation metrics. Additionally, we discuss fundamental challenges, limitations, and promising research directions in this evolving field. Relevant papers and resources are continuously updated at the Github Repo ( https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent ).
- 11 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (4) , 1-39
Top Cited PapersOpen AccessA Survey of Personalization: From RAG to Agent
Personalization has become an essential capability in modern AI systems, enabling customized interactions that align with individual user preferences, contexts, and goals. Recent research has increasingly concentrated on Retrieval-Augmented Generation (RAG) frameworks and their evolution into more advanced agent-based architectures within personalized settings to enhance user satisfaction. Building on this foundation, this survey systematically examines personalization across the three core stages of RAG: pre-retrieval, retrieval, and generation. Beyond RAG, we further extend its capabilities into the realm of Personalized LLM-based Agents, which enhance traditional RAG systems with agentic functionalities, including user understanding, personalized planning and execution, and dynamic generation. For both personalization in RAG and agent-based personalization, we provide formal definitions, conduct a comprehensive review of recent literature, and summarize key datasets and evaluation metrics. Additionally, we discuss fundamental challenges, limitations, and promising research directions in this evolving field. Relevant papers and resources are continuously updated at the Github Repo ( https://github.com/Applied-Machine-Learning-Lab/Awesome-Personalized-RAG-Agent ).
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2878-2889
Exploring Recommender System Evaluation: A Multi-Modal LLM Agent Framework for A/B Testing
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2878-2889
Open AccessExploring Recommender System Evaluation: A Multi-Modal LLM Agent Framework for A/B Testing
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2049-2059
To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive searches as they cannot accurately judge when to stop searching and start answering. This stems from outcome-centric training that prioritize final results over the search process itself. We identify the root cause as misaligned decision boundaries, the threshold determining when accumulated information suffices to answer. This causes over-search (redundant searching despite sufficient knowledge) and under-search (premature termination yielding incorrect answers). To address these errors, we propose a comprehensive framework comprising two key components. First, we introduce causal intervention-based diagnosis that identifies boundary errors by comparing factual and counterfactual trajectories at each decision point. Second, we develop Decision Boundary Alignment for Deep Search agents (DAS), which constructs preference datasets from causal feedback and aligns policies via preference optimization. Experiments on public datasets demonstrate that decision boundary errors are pervasive across state-of-the-art agents. Our DAS method effectively calibrates these boundaries, mitigating both over-search and under-search to achieve substantial gains in accuracy and efficiency. Our code and data are publicly available at: https://github.com/Applied-Machine-Learning-Lab/WWW2026_DAS.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2049-2059
Open AccessTo Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive searches as they cannot accurately judge when to stop searching and start answering. This stems from outcome-centric training that prioritize final results over the search process itself. We identify the root cause as misaligned decision boundaries, the threshold determining when accumulated information suffices to answer. This causes over-search (redundant searching despite sufficient knowledge) and under-search (premature termination yielding incorrect answers). To address these errors, we propose a comprehensive framework comprising two key components. First, we introduce causal intervention-based diagnosis that identifies boundary errors by comparing factual and counterfactual trajectories at each decision point. Second, we develop Decision Boundary Alignment for Deep Search agents (DAS), which constructs preference datasets from causal feedback and aligns policies via preference optimization. Experiments on public datasets demonstrate that decision boundary errors are pervasive across state-of-the-art agents. Our DAS method effectively calibrates these boundaries, mitigating both over-search and under-search to achieve substantial gains in accuracy and efficiency. Our code and data are publicly available at: https://github.com/Applied-Machine-Learning-Lab/WWW2026_DAS.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6389-6399
BlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations
Transformer structures have been widely used in sequential recommender systems (SRS). However, as user interaction histories increase, computational time and memory requirements also grow. This is mainly caused by the standard attention mechanism. Although there exist many methods employing efficient attention and SSM-based models, these approaches struggle to effectively model long sequences and may exhibit unstable performance on short sequences. To address these challenges, we design a sparse attention mechanism, BlossomRec, which models both long-term and short-term user interests through attention computation to achieve stable performance across sequences of varying lengths. Specifically, we categorize user interests in recommendation systems into long-term and short-term interests, and compute them using two distinct sparse attention patterns, with the results combined through a learnable gated output. Theoretically, it significantly reduces the number of interactions participating in attention computation. Extensive experiments on four public datasets demonstrate that BlossomRec, when integrated with state-of-the-art Transformer-based models, achieves comparable or even superior performance while significantly reducing memory usage, providing strong evidence of BlossomRec's efficiency and effectiveness. The code is available at https://github.com/Applied-Machine-Learning-Lab/WWW2026_BlossomRec.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6389-6399
Open AccessBlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations
Transformer structures have been widely used in sequential recommender systems (SRS). However, as user interaction histories increase, computational time and memory requirements also grow. This is mainly caused by the standard attention mechanism. Although there exist many methods employing efficient attention and SSM-based models, these approaches struggle to effectively model long sequences and may exhibit unstable performance on short sequences. To address these challenges, we design a sparse attention mechanism, BlossomRec, which models both long-term and short-term user interests through attention computation to achieve stable performance across sequences of varying lengths. Specifically, we categorize user interests in recommendation systems into long-term and short-term interests, and compute them using two distinct sparse attention patterns, with the results combined through a learnable gated output. Theoretically, it significantly reduces the number of interactions participating in attention computation. Extensive experiments on four public datasets demonstrate that BlossomRec, when integrated with state-of-the-art Transformer-based models, achieves comparable or even superior performance while significantly reducing memory usage, providing strong evidence of BlossomRec's efficiency and effectiveness. The code is available at https://github.com/Applied-Machine-Learning-Lab/WWW2026_BlossomRec.
- Open Access
- 4 December 2025
- Published by MDPI AG in Preprints.org
A Survey of Generative Recommendation from a Tri-Decoupled Perspective: Tokenization, Architecture, and Optimization
The recommender systems community is witnessing a rapid shift from multi-stage cascaded discriminative pipelines (retrieval, ranking, and re-ranking) toward unified generative frameworks that directly generate items. Compared with traditional discriminative models, generative recommender systems offer the potential to mitigate cascaded error propagation, improve hardware utilization through unified architectures, and optimize beyond local user behaviors. This emerging paradigm has been catalyzed by the rise of generative models and the demand for end-to-end architectures that significantly improve Model FLOPS Utilization (MFU). In this survey, we provide a comprehensive analysis of generative recommendation through tri-decoupled perspective of tokenization, architecture, and optimization, three foundational components that collectively define existing generative systems. We trace the evolution of tokenization from sparse ID- and text-based encodings to semantic identifiers that balance vocabulary efficiency with semantic expressiveness; analyze encoder–decoder, decoder-only, and diffusion-based architectures that increasingly adopt unified, scalable, and efficient backbones; and review the transition from supervised next-token prediction to reinforcement learning–based preference alignment enabling multi-dimensional preference optimization. We further summarize practical deployments across cascade stages and application scenarios, and examine key open challenges. Taken together, this survey is intended to serve as a foundational reference for the research community and as an actionable blueprint for industrial practitioners building next-generation generative recommender systems. To support ongoing research, we maintain a living repository https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec}{https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec that continuously tracks emerging literature and reference implementations.
- 4 December 2025
- Published by MDPI AG in Preprints.org
Open AccessA Survey of Generative Recommendation from a Tri-Decoupled Perspective: Tokenization, Architecture, and Optimization
The recommender systems community is witnessing a rapid shift from multi-stage cascaded discriminative pipelines (retrieval, ranking, and re-ranking) toward unified generative frameworks that directly generate items. Compared with traditional discriminative models, generative recommender systems offer the potential to mitigate cascaded error propagation, improve hardware utilization through unified architectures, and optimize beyond local user behaviors. This emerging paradigm has been catalyzed by the rise of generative models and the demand for end-to-end architectures that significantly improve Model FLOPS Utilization (MFU). In this survey, we provide a comprehensive analysis of generative recommendation through tri-decoupled perspective of tokenization, architecture, and optimization, three foundational components that collectively define existing generative systems. We trace the evolution of tokenization from sparse ID- and text-based encodings to semantic identifiers that balance vocabulary efficiency with semantic expressiveness; analyze encoder–decoder, decoder-only, and diffusion-based architectures that increasingly adopt unified, scalable, and efficient backbones; and review the transition from supervised next-token prediction to reinforcement learning–based preference alignment enabling multi-dimensional preference optimization. We further summarize practical deployments across cascade stages and application scenarios, and examine key open challenges. Taken together, this survey is intended to serve as a foundational reference for the research community and as an actionable blueprint for industrial practitioners building next-generation generative recommender systems. To support ongoing research, we maintain a living repository https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec}{https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec that continuously tracks emerging literature and reference implementations.