Qingpeng Cai is currently a Senior Director & Principal Scientist at Kuaishou Technology. He received his Ph.D. from Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University. He received his B.E. from Nanjing University. His core research focuses on Reinforcement Learning and its applications to Large Language Models and practical domains (Recommender Systems and Advertising). He serves as Area Chair for top-tier machine learning conferences including NeurIPS, ICLR. He was awarded WSDM 2026 Best Full Research Paper Runner-up Award and dual-track championships(1/1500) in the NeurIPS 2024 Auto-Bidding in Large-Scale Auctions Competition.

蔡庆芃目前在快手科技担任资深总监&首席科学家。他于清华大学交叉信息研究院获得博士学位，本科毕业于南京大学。他的研究兴趣专注在强化学习以及其在大语言模型以及实际问题（推荐、广告领域）的应用。他担任NeurIPS, ICLR等机器学习顶级会议的领域主席。他曾获得WSDM 2026最佳长文提名奖、NeurIPS 2024自动出价比赛双赛道冠军(1/1500)、2024年钱伟长中文信息处理科学技术奖（自然科学一等奖）。

Professional Activities

• Organizer: Agent-based Information Retrieval Workshop @SIGIR 2024, SIGIR 2025

• Area Chair/Senior Program Committee: NeurIPS, ICLR, CIKM

Preprint(* indicates the corresponding author)

• 1.Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration [pdf]
  Jingtong Gao, Ling Pan, Yejing Wang, Rui Zhong, Chi Lu, Qingpeng Cai*, Peng Jiang, Xiangyu Zhao
  

• 2.Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner [pdf]
  Yewen Li, Jingtong Gao, Nan Jiang, Shuai Mao, Ruyi An, Fei Pan, Xiangyu Zhao, Bo An, Qingpeng Cai*, Peng Jiang
  

• 3.MindRec: A Diffusion-driven Coarse-to-Fine Paradigm for Generative Recommendation [pdf]
  Mengyao Gao, Chongming Gao, Haoyan Liu, Qingpeng Cai, Peng Jiang, Jiajia Chen, Shuai Yuan, Xiangnan He
  

• 4.Integrating Large Language Models with Reinforcement Learning: A Survey of LLM-RL Synergistic Recommendation [pdf]
  Mengyao Gao, Chongming Gao, Jiakai Tang, Jingsen Zhang, Xinpeng Zhao, Bohao Wang, Jiawei Chen, Haoran He, Ling Pan, Xu Chen, Xin Xin, Qingpeng Cai*, Peng Jiang, Kun Gai, Haoyan Liu, Fuli Feng, Xiangnan He
  

Publications(* indicates the corresponding author)

• 41.Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards [pdf]
  Haoran He, Yuxiao Ye, Qingpeng Cai, Chen Hu, Binxing Jiao, Daxin Jiang, Ling Pan
  ICLR-2026
  

• 40.TrackRec: Iterative Alternating Feedback with Chain-of-Thought via Preference Alignment for Recommendation [pdf]
  Yu Xia, Rui Zhong, Zeyu Song, Wei Yang, Junchen Wan, Qingpeng Cai, Chi Lu, Peng Jiang
  DASFAA-2026
  

• 39. LBM: Hierarchical Large Auto-Bidding Model with Reasoning and Acting
  Yewen Li, Zhiyi Lyu, Peng Jiang, Qingpeng Cai*, Fei Pan, Bo An, Peng Jiang
  WWW-2026, Oral
  

• 38.Hierarchical Semantic RL: Tackling the Problem of Dynamic Action Space for RL-based Recommendations [pdf]
  Minmao Wang, Xingchen Liu, Shijie Yi, Likang Wu, Hongke Zhao, Fei Pan, Qingpeng Cai*, Peng Jiang
  WWW-2026, Oral
  

• 37.TemporalExpertNet: Cross-Temporal Knowledge Reuse for Promotion-Aware CVR Prediction
  Minmao Wang, Rui Zhang, Shijie Yi, Likang Wu, Hongke Zhao, Fei Pan, Qingpeng Cai*, Peng Jiang
  (WSDM-2026, Best Full Research Paper Runner-up)
  

• 36.Random Policy Evaluation Uncovers Policies of Generative Flow Networks
  Haoran He, Emmanuel Bengio, Qingpeng Cai, Ling Pan
  ICML-2025
  

• 35.LLM-Powered Efficient User Simulator for Recommender System [pdf]
  Zijian Zhang, Shuchang Liu, Ziru Liu, Rui Zhong, Qingpeng Cai*, Xiangyu Zhao, Chunxu Zhang, Qidong Liu, Peng Jiang
  AAAI-2025, Oral
  

• 34.Flow Factorization for Efficient Generative Flow Networks [pdf]
  Jiashun Liu, Chunhui Li, Cheng-Hao Liu, Dianbo Liu, Qingpeng Cai, Ling Pan
  AAAI-2025, Oral
  

• 33.DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems [pdf]
  Jiaju Chen, Chongming Gao, Shuai Yuan, Shuchang Liu, Qingpeng Cai, Peng Jiang
  WSDM-2025
  

• 32.Generative Auto-Bidding with Value-Guided Explorations[pdf]
  Jingtong Gao, Yewen Li, Shuai Mao, Peng Jiang, Nan Jiang, Yejing Wang, Qingpeng Cai*, Fei Pan, Peng Jiang, Kun Gai, Bo An, Xiangyu Zhao
  SIGIR-2025
  

• 31.GAS: Generative Auto-bidding with Post-training Search [pdf]
  Yewen Li, Shuai Mao, Jingtong Gao, Nan Jiang, Yunjian Xu, Qingpeng Cai*, Fei Pan, Peng Jiang, Bo An
  WWW-2025, Industry Track
  

• 30.AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems[pdf]
  Zhenghai Xue, Qingpeng Cai*, Tianyou Zuo, Bin Yang, Lantao Hu, Peng Jiang, Kun Gai, Bo An
  WWW-2025, Oral
  

• 29.Value Function Decomposition in Markov Recommendation Process[pdf]
  Xiaobei Wang, Shuchang Liu, Qingpeng Cai, Xiang Li, Lantao Hu, Han Li, Guangming Xie
  WWW-2025, Oral
  

• 28.Modeling User Retention through Generative Flow Networks [pdf]
  Ziru Liu, Shuchang Liu, Bin Yang, Zhenghai Xue, Qingpeng Cai*, Xiangyu Zhao, Zijian Zhang, Lantao Hu, Han Li, Peng Jiang
  KDD-2024, industry track
  

• 27.Future Impact Decomposition in Request-level Recommendations [pdf]
  Xiaobei Wang, Shuchang Liu, Xueliang Wang, Qingpeng Cai*, Lantao Hu, Han Li, Peng Jiang, Guangming Xie
  KDD-2024, industry track
  

• 26.Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention [pdf]
  Ziru Liu, Shuchang Liu, Zijian Zhang, Qingpeng Cai*, Xiangyu Zhao, Kesen Zhao, Lantao Hu, Peng Jiang, Kun Gai
  SIGIR-2024
  

• 25.M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework [pdf]
  Zijian Zhang, Shuchang Liu, Jiaao Yu, Qingpeng Cai, Xiangyu Zhao, Chunxu Zhang, Ziru Liu, Qidong Liu, Hongwei Zhao, Lantao Hu, Peng Jiang, Kun Gai
  SIGIR-2024
  

• 24.State Regularized Policy Optimization on Data with Dynamics Shift [pdf]
  Zhenghai Xue, Qingpeng Cai, Shuchang Liu, Dong Zheng, Peng Jiang, Kun Gai, Bo An
  NeurIPS-2023
  

• 23.KuaiSim: A Comprehensive Simulator for Recommender Systems [pdf]
  Kesen Zhao, Shuchang Liu, Qingpeng Cai*, Xiangyu Zhao, Ziru Liu, Dong Zheng, Peng Jiang, Kun Gai
  NeurIPS-2023
  

• 22.ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor [pdf]
  Wanqi Xue, Qingpeng Cai, Ruohan Zhan, Dong Zheng, Peng Jiang, Kun Gai, Bo An
  ICLR-2023
  

• 21.PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement [pdf]
  Wanqi Xue, Qingpeng Cai, Zhenghai Xue, Shuo Sun, Shuchang Liu, Dong Zheng, Peng Jiang, Kun Gai, Bo An
  KDD-2023
  

• 20.Generative Flow Network for Listwise Recommendation [pdf]
  Shuchang Liu, Qingpeng Cai, Zhankui He, Bowen Sun, Julian McAuley, Dong Zheng, Peng Jiang, Kun Gai
  KDD-2023
  

• 19.Multi-Task Recommendations with Reinforcement Learning [pdf]
  Ziru Liu, Jiejie Tian, Qingpeng Cai*, Xiangyu Zhao, Jingtong Gao, Shuchang Liu, Dayou Chen, Tonghao He, Dong Zheng, Peng Jiang and Kun Gai
  WWW-2023
  

• 18.Exploration and Regularization of the Latent Action Space in Recommendation [pdf]
  Shuchang Liu, Qingpeng Cai, Bowen Sun, Yuhao Wang, Dong Zheng, Peng Jiang, Kun Gai, Ji Jiang, Xiangyu Zhao and Yongfeng Zhang
  WWW-2023
  

• 17.Two-Stage Constrained Actor-Critic for Short Video Recommendation [pdf]
  Qingpeng Cai, Zhenghai Xue, Chi Zhang, Wanqi Xue, Shuchang Liu, Ruohan Zhan, Xueliang Wang, Tianyou Zuo, Wentao Xie, Dong Zheng, Peng Jiang and Kun Gai
  WWW-2023
  

• 16.Reinforcing User Retention in a Billion Scale Short Video Recommender System [pdf]
  Qingpeng Cai, Shuchang Liu, Xueliang Wang, Tianyou Zuo, Wentao Xie, Bin Yang, Dong Zheng, Peng Jiang and Kun Gai
  WWW-2023, industry track
  

• 15.Exploration in policy optimization through multiple paths
  Ling Pan, Qingpeng Cai, Longbo Huang
  JAAMAS-2021
  

• 14.Softmax Deep Double Deterministic Policy Gradients [pdf]
  Ling Pan, Qingpeng Cai, Longbo Huang
  NeurIPS-2020
  

• 13.Reinforcement Learning with Dynamic Boltzmann Softmax Updates [pdf]
  Ling Pan, Qingpeng Cai, Qi Meng, Wei Chen, Longbo Huang
  IJCAI-2020
  

• 12.Multi-path Policy Optimization [pdf]
  Ling Pan, Qingpeng Cai, Longbo Huang
  AAMAS-2020
  (Invited for fast-track publication in JAAMAS, top 5%)
  

• 11.Deterministic Value-Policy Gradients [pdf]
  Qingpeng Cai, Ling Pan, Pingzhong Tang
  AAAI-2020
  

• 10.Policy optimization with model-based explorations
  Feiyang Pan, Qingpeng Cai, An-Xiang Zeng, Chun-Xiang Pan, Qing Da, Hualin He, Qing He, Pingzhong Tang
  AAAI-2019
  

• 9.A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems [pdf]
  Ling Pan, Qingpeng Cai, Zhixuan Fang, Pingzhong Tang, Longbo Huang
  AAAI-2019
  

• 8.Reinforcement Learning Driven Heuristic Optimization [pdf]
  Qingpeng Cai, Will Hang, Azalia Mirhoseini, George Tucker, Jingtao Wang, Wei Wei
  DRL4KDD-2019
  

• 7.Policy gradients for contextual recommendations
  Feiyang Pan, Qingpeng Cai, Pingzhong Tang, Fuzhen Zhuang, Qing He
  WWW-2019
  

• 6.Reinforcement Mechanism Design for E-commerce [pdf]
  Qingpeng Cai, Aris Filos-Ratsikas, Pingzhong Tang, Yiwei Zhang
  WWW-2018
  

• 5.Reinforcement Mechanism Design for Fraudulent Behaviour in E-commerce [pdf]
  Qingpeng Cai, Aris Filos-Ratsikas, Pingzhong Tang, Yiwei Zhang
  AAAI-2018
  

• 4.Ranking Mechanism Design for Price-setting Agents in E-commerce [pdf]
  Qingpeng Cai, Pingzhong Tang, Yulong Zeng
  AAMAS-2018
  

• 3.Multi-armed Bandit Mechanism With Private Histories [pdf]
  Chang Liu, Qingpeng Cai, Yukui Zhang
  AAMAS-2017 (Extended abstract)
  

• 2.Facility location with Minimax Envy [pdf]
  Qingpeng Cai, Aris Filos-Ratsikas, Pingzhong Tang
  IJCAI-2016
  

• 1.Mechanism Design for Personalized Recommender Systems [pdf]
  Qingpeng Cai, Aris Filos-Ratsikas, Chang Liu, Pingzhong Tang
  Recsys-2016