Sunhao Dai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sunhao Dai has a total of 103 co-authors. Here are the top co-authors by number of shared publications:
- Jun Xu
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
20 shared publications - Liang Pang
State Key Lab of AI Safety, Institute of Computing Technology, CAS, Beijing, China
8 shared publications - Xiao Zhang
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
7 shared publications - Jiakai Tang
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China, Beijing Key Laboratory of Research on Large Models and Intelligent Governance, Beijing, China, and Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE, Beijing, China
6 shared publications - Xu Chen
Sun Yat-Sen University, Guangzhou, China
6 shared publications - Ji-Rong Wen
Gaoling School of Artificial Intelligence, Renmin University of China, China
5 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4258-4269
CaLR: Context-Aware Latent Reasoning for Sequential Recommendation
Sequential recommendation aims to model users' evolving preferences from their historical interactions. Recent latent reasoning methods improve sequential recommenders by extending inferencetime computation in continuous representation space, refining user representations without generating explicit reasoning text. However, existing methods mainly reason over the encoded history itself and make limited use of contextual feedback from users' recent interactions. Such feedback, especially positive and negative signals in the latest session, can not only complement the long-term user representation but also provide directional guidance for latent reasoning by indicating which preference patterns should be strengthened or suppressed. In this paper, we propose Context-Aware Latent Reasoning (CaLR), a model-agnostic framework that grounds latent reasoning in session-level context. From the input perspective, CaLR selects informative positive and negative items from users' recent sessions as reasoning anchors. From the architecture perspective, it injects these anchors into each reasoning step through a Cross-Attention-based module. From the optimization perspective, it introduces Process Supervision Loss (PSL) to supervise intermediate reasoning states according to anchor feedback polarity. Experiments on two real-world public benchmarks show that CaLR consistently improves multiple sequential recommendation backbones and outperforms strong latent reasoning baselines. Ablation and further analyses verify the effectiveness of each component in CaLR. Moreover, a seven-day online A/B test on Kuaishou Lite demonstrates its effectiveness in real-world industrial deployment. Our code is available at https://github.com/Ak4ne-windsky/CaLR.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4258-4269
Open AccessCaLR: Context-Aware Latent Reasoning for Sequential Recommendation
Sequential recommendation aims to model users' evolving preferences from their historical interactions. Recent latent reasoning methods improve sequential recommenders by extending inferencetime computation in continuous representation space, refining user representations without generating explicit reasoning text. However, existing methods mainly reason over the encoded history itself and make limited use of contextual feedback from users' recent interactions. Such feedback, especially positive and negative signals in the latest session, can not only complement the long-term user representation but also provide directional guidance for latent reasoning by indicating which preference patterns should be strengthened or suppressed. In this paper, we propose Context-Aware Latent Reasoning (CaLR), a model-agnostic framework that grounds latent reasoning in session-level context. From the input perspective, CaLR selects informative positive and negative items from users' recent sessions as reasoning anchors. From the architecture perspective, it injects these anchors into each reasoning step through a Cross-Attention-based module. From the optimization perspective, it introduces Process Supervision Loss (PSL) to supervise intermediate reasoning states according to anchor feedback polarity. Experiments on two real-world public benchmarks show that CaLR consistently improves multiple sequential recommendation backbones and outperforms strong latent reasoning baselines. Ablation and further analyses verify the effectiveness of each component in CaLR. Moreover, a seven-day online A/B test on Kuaishou Lite demonstrates its effectiveness in real-world industrial deployment. Our code is available at https://github.com/Ak4ne-windsky/CaLR.
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4291-4302
Latent Residual Reasoning for Ranking in Generative Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4291-4302
Open AccessLatent Residual Reasoning for Ranking in Generative Recommendation
- Open Access
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-45
RecGPT: A User Intent-Centric Next-Generation LLM-Powered Recommender System in Industrial Practice
Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most 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’ potential interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a fully integrated, production-ready 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 (e.g., CICD +5.53%, DT +4.35%), merchants and the platform gain greater exposure and conversions (e.g., CTR +5.65%, IPV +7.55%, DCAU +2.46%), and sustained long-term retention improvements (LT-30 +1.63%). These comprehensive improvement results across all stakeholders validate that our intent-centric design can foster a more sustainable and mutually beneficial ecosystem.
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-45
Open AccessRecGPT: A User Intent-Centric Next-Generation LLM-Powered Recommender System in Industrial Practice
Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most 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’ potential interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a fully integrated, production-ready 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 (e.g., CICD +5.53%, DT +4.35%), merchants and the platform gain greater exposure and conversions (e.g., CTR +5.65%, IPV +7.55%, DCAU +2.46%), and sustained long-term retention improvements (LT-30 +1.63%). These comprehensive improvement results across all stakeholders validate that our intent-centric design can foster a more sustainable and mutually beneficial ecosystem.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7117-7128
OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7117-7128
Open AccessOnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8053-8064
OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation
Multi-task learning (MTL) is essential in recommender systems to enable complementary learning among diverse user feedback. While modern industrial practices have shifted from DNNs to Transformer-centric architectures to strengthen sequence modeling and scaling capacity, they still decouple feature encoding from multi-task prediction, treating the Transformer as a task-agnostic encoder. This design fundamentally limits the performance and scalability by (1) creating an information bottleneck under heterogeneous task objectives, (2) inducing gradient interference that leads to the seesaw phenomenon, and (3) forcing a dataflow transition in which attention-based, context-adaptive representation learning is converted to static feed-forward task prediction with incompatible information read–write dynamics. In this paper, we propose OneRank, a Transformer-native multi-task ranking framework that eliminates the encoder–predictor separation and introduces task-private channels for both forward representation learning and backward optimization, enabling task-specialized learning while minimizing inter-task interferences. In the forward pass, OneRank learns task-specific representations in a bottom-up manner through task-conditioned information selection, candidate–aware contextualization, and controlled cross-task interaction. In the backward pass, cross-task gradient detachment isolates task-private parameter updates from shared knowledge extraction modules, preventing negative transfer. Finally, we replace static task-specific MLP scorers with a dynamic matching-based scoring formulation for context-aware personalized ranking. By internalizing multi-task reasoning pathways within the Transformer stack, OneRank establishes a new architectural paradigm with unified modeling and scalable computation design. Extensive offline and online experiments on large-scale industrial datasets demonstrate that OneRank significantly outperforms state-of-the-art baselines across multiple tasks, with substantial improvements in ranking effectiveness while maintaining computational efficiency.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8053-8064
Open AccessOneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation
Multi-task learning (MTL) is essential in recommender systems to enable complementary learning among diverse user feedback. While modern industrial practices have shifted from DNNs to Transformer-centric architectures to strengthen sequence modeling and scaling capacity, they still decouple feature encoding from multi-task prediction, treating the Transformer as a task-agnostic encoder. This design fundamentally limits the performance and scalability by (1) creating an information bottleneck under heterogeneous task objectives, (2) inducing gradient interference that leads to the seesaw phenomenon, and (3) forcing a dataflow transition in which attention-based, context-adaptive representation learning is converted to static feed-forward task prediction with incompatible information read–write dynamics. In this paper, we propose OneRank, a Transformer-native multi-task ranking framework that eliminates the encoder–predictor separation and introduces task-private channels for both forward representation learning and backward optimization, enabling task-specialized learning while minimizing inter-task interferences. In the forward pass, OneRank learns task-specific representations in a bottom-up manner through task-conditioned information selection, candidate–aware contextualization, and controlled cross-task interaction. In the backward pass, cross-task gradient detachment isolates task-private parameter updates from shared knowledge extraction modules, preventing negative transfer. Finally, we replace static task-specific MLP scorers with a dynamic matching-based scoring formulation for context-aware personalized ranking. By internalizing multi-task reasoning pathways within the Transformer stack, OneRank establishes a new architectural paradigm with unified modeling and scalable computation design. Extensive offline and online experiments on large-scale industrial datasets demonstrate that OneRank significantly outperforms state-of-the-art baselines across multiple tasks, with substantial improvements in ranking effectiveness while maintaining computational efficiency.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4580-4591
Interactive Recommendation Agent with Active User Commands
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4580-4591
Open AccessInteractive Recommendation Agent with Active User Commands
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3356-3364
KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3356-3364
Open AccessKuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2544-2555
Learning to Retrieve from Agent Trajectories
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2544-2555
Open AccessLearning to Retrieve from Agent Trajectories
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1-15
Think before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation
Sequential Recommendation (SeqRec) aims to predict the next item by capturing sequential patterns from users' historical interactions, playing a crucial role in many real-world recommender systems. However, existing approaches predominantly adopt a direct forward computation paradigm, where the final hidden state of the sequence encoder serves as the user representation. We argue that this inference paradigm, due to its limited computational depth, struggles to model the complex evolving nature of user preferences and lacks a nuanced understanding of long-tail items, leading to suboptimal performance. To address this issue, we propose ReaRec, the first inference-time computing framework for recommender systems, which enhances user representations through implicit multi step reasoning. Specifically, ReaRecautoregressively feeds the sequence's last hidden state into the sequential recommender while incorporating special reasoning position embeddings to decouple the original item encoding space from the multi step reasoning space. Moreover, we introduce two lightweight reasoning-based learning methods, Ensemble Reasoning Learning (ERL) and Progressive Reasoning Learning (PRL), to further effectively exploit ReaRec's reasoning potential. Extensive experiments on five public real-world datasets and different SeqRec architectures demonstrate the generality and effectiveness of our proposed ReaRec. Remarkably, post-hoc analyses reveal that ReaRec significantly elevates the performance ceiling of multiple sequential recommendation backbones by approximately 30% 50%. Thus, we believe this work can open a new and promising avenue for future research in inference-time computing for sequential recommendation. The source code is available at https://github.com/TangJiakai/ReaRec.git.
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1-15
Think before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation
Sequential Recommendation (SeqRec) aims to predict the next item by capturing sequential patterns from users' historical interactions, playing a crucial role in many real-world recommender systems. However, existing approaches predominantly adopt a direct forward computation paradigm, where the final hidden state of the sequence encoder serves as the user representation. We argue that this inference paradigm, due to its limited computational depth, struggles to model the complex evolving nature of user preferences and lacks a nuanced understanding of long-tail items, leading to suboptimal performance. To address this issue, we propose ReaRec, the first inference-time computing framework for recommender systems, which enhances user representations through implicit multi step reasoning. Specifically, ReaRecautoregressively feeds the sequence's last hidden state into the sequential recommender while incorporating special reasoning position embeddings to decouple the original item encoding space from the multi step reasoning space. Moreover, we introduce two lightweight reasoning-based learning methods, Ensemble Reasoning Learning (ERL) and Progressive Reasoning Learning (PRL), to further effectively exploit ReaRec's reasoning potential. Extensive experiments on five public real-world datasets and different SeqRec architectures demonstrate the generality and effectiveness of our proposed ReaRec. Remarkably, post-hoc analyses reveal that ReaRec significantly elevates the performance ceiling of multiple sequential recommendation backbones by approximately 30% 50%. Thus, we believe this work can open a new and promising avenue for future research in inference-time computing for sequential recommendation. The source code is available at https://github.com/TangJiakai/ReaRec.git.
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 442-446
Trustworthy Information Retrieval in the LLM Era: Bias, Unfairness, and Hallucination
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 442-446
Open AccessTrustworthy Information Retrieval in the LLM Era: Bias, Unfairness, and Hallucination