Fangkai Yang

Senior Researcher

Publications

View by:

- Beyond State Consistency: Behavior Consistency in Text-Based World Models
  
  Youling Huang, Guanqiao Chen, Junchi Yao, Lu Wang, Fangkai Yang, Chao Du, ChenZhuo Zhao, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
  
  April 2026
  
  Publication
- DUET: Joint Exploration of User Item Profiles in Recommendation System
  
  Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yi Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
  
  April 2026
  
  Publication
- Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
  
  Qibin Wang, Pu Zhao, Shaohan Huang, Fangkai Yang, Lu Wang, Furu Wei, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | August 2025, Vol abs/2509.00084
  
  DOI Publication Publication
- ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud
  
  Lu Wang, Mayukh Das, Fangkai Yang, Bo Qiao, Hang Dong, Si Qin, Victor Ruehle, Chetan Bansal, Eli Cortez, Íñigo Goiri, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  MLSys'25 | May 2025
  
  Publication
- UFO2: The Desktop AgentOS
  
  Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, Liqun Li, Yu Kang, Zhao Jiang, Suzhen Zheng, Rujia Wang, Jiaxu Qian, Ming-Jie Ma, Jianjun Lou, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | April 2025, Vol abs/2504.14603
  
  DOI Publication Publication Project Project
- Pretrain Value, Not Reward: Decoupled Value Policy Optimization
  
  Chenghua Huang, Lu Wang, Fangkai Yang, Pu Zhao, Zhixu Li, Qingwei Lin 林庆维, Dongmei Zhang, S. Rajmohan, Qi Zhang
  
  ICLR 2026 | February 2025
  
  Publication
- ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
  
  Minghua He, Fangkai Yang, Pu Zhao, Wenjie Yin, Yu Kang, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.18460
  
  DOI Publication Publication Project
- Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
  
  Xing Zhang, Jiaheng Wen, Fangkai Yang, Pu Zhao, Yu Kang, Junhao Wang, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin 林庆维, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.16050
  
  DOI Publication Publication Project
- Enabling Autonomic Microservice Management through Self-Learning Agents
  
  Fenglin Yu, Fangkai Yang, Xiaoting Qin, Zhiyang Zhang, Jue Zhang, Qingwei Lin 林庆维, Hongyu Zhang, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  January 2025
  
  Preprint
- AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation
  
  Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin 林庆维, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  EMNLP'24 | November 2024
  
  Preprint
- COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty
  
  Lu Wang, Mayukh Das, Fangkai Yang, Chao Du, Bo Qiao, Hang Dong, Chetan Bansal, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang, Qi Zhang
  
  CIKM'24 | October 2024
  
  PDF
- AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
  
  Xi Chen, Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Chao Du, Xi Cheng, Hangxin Liu, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  September 2024
  
  Preprint
- Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
  
  Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin, Xiang Huang, Ling Chen, Qingwei Lin 林庆维, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  ACL 2024 | August 2024
  
  Publication
- The Vision of Autonomic Computing: Can LLMs Make It a Reality?
  
  Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Jue Zhang, Qingwei Lin 林庆维, Gong Cheng, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  July 2024
  
  Preprint
- TaskWeaver: A Code-First Agent Framework
  
  Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  December 2023
  
  Publication
- Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets
  
  Fangkai Yang, Jue Zhang, Lu Wang, Bo Qiao, Di Weng, Xiaoting Qin, Gregory Weber, Durgesh Nandini Das, Srinivasan Rakhunathan, Ranganathan Srikanth, Qingwei Lin 林庆维, Dongmei Zhang
  
  2023 Knowledge Discovery and Data Mining | August 2023
  
  Publication
- Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
  
  Junjie Sheng, Lu Wang, Fangkai Yang, Bo Qiao, Hang Dong, Xiangfeng Wang, Bo Jin, Jun Wang, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW '23 | April 2023
  
  DOI
- Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-Demand VMs
  
  Fangkai Yang, Lu Wang, Zhenyu Xu, Jue Zhang, Liqun Li, Bo Qiao, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Terry Yang, Victor Ruehle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  ASPLOS'23 | March 2023
  
  Publication
- NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365
  
  Lu Wang, Pu Zhao, Chao Du, Chuan Luo, Mengna Su, Fangkai Yang, Yudong Liu, Qingwei Lin 林庆维, Min Wang, Yingnong Dang, Hongyu Zhang, Saravan Rajmohan, Dongmei Zhang
  
  SIGKDD 2022 | August 2022
  
  Publication Project Project
- Spot Virtual Machine Eviction Prediction in Microsoft Cloud
  
  Fangkai Yang, Bowen Pang, Jue Zhang, Bo Qiao, Lu Wang, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Senthil Baladhandayutham, Victor Rühle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW'22 Companion | April 2022
  
  Publication

- DUET: Joint Exploration of User Item Profiles in Recommendation System
  
  Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yi Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
  
  April 2026
  
  Publication
- Beyond State Consistency: Behavior Consistency in Text-Based World Models
  
  Youling Huang, Guanqiao Chen, Junchi Yao, Lu Wang, Fangkai Yang, Chao Du, ChenZhuo Zhao, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
  
  April 2026
  
  Publication
- Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
  
  Qibin Wang, Pu Zhao, Shaohan Huang, Fangkai Yang, Lu Wang, Furu Wei, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | August 2025, Vol abs/2509.00084
  
  DOI Publication Publication
- ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud
  
  Lu Wang, Mayukh Das, Fangkai Yang, Bo Qiao, Hang Dong, Si Qin, Victor Ruehle, Chetan Bansal, Eli Cortez, Íñigo Goiri, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  MLSys'25 | May 2025
  
  Publication
- UFO2: The Desktop AgentOS
  
  Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, Liqun Li, Yu Kang, Zhao Jiang, Suzhen Zheng, Rujia Wang, Jiaxu Qian, Ming-Jie Ma, Jianjun Lou, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | April 2025, Vol abs/2504.14603
  
  DOI Publication Publication Project Project
- Pretrain Value, Not Reward: Decoupled Value Policy Optimization
  
  Chenghua Huang, Lu Wang, Fangkai Yang, Pu Zhao, Zhixu Li, Qingwei Lin 林庆维, Dongmei Zhang, S. Rajmohan, Qi Zhang
  
  ICLR 2026 | February 2025
  
  Publication
- ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
  
  Minghua He, Fangkai Yang, Pu Zhao, Wenjie Yin, Yu Kang, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.18460
  
  DOI Publication Publication Project
- Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
  
  Xing Zhang, Jiaheng Wen, Fangkai Yang, Pu Zhao, Yu Kang, Junhao Wang, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin 林庆维, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.16050
  
  DOI Publication Publication Project
- Enabling Autonomic Microservice Management through Self-Learning Agents
  
  Fenglin Yu, Fangkai Yang, Xiaoting Qin, Zhiyang Zhang, Jue Zhang, Qingwei Lin 林庆维, Hongyu Zhang, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  January 2025
  
  Preprint
- AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation
  
  Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin 林庆维, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  EMNLP'24 | November 2024
  
  Preprint
- COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty
  
  Lu Wang, Mayukh Das, Fangkai Yang, Chao Du, Bo Qiao, Hang Dong, Chetan Bansal, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang, Qi Zhang
  
  CIKM'24 | October 2024
  
  PDF
- AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
  
  Xi Chen, Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Chao Du, Xi Cheng, Hangxin Liu, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  September 2024
  
  Preprint
- Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
  
  Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin, Xiang Huang, Ling Chen, Qingwei Lin 林庆维, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  ACL 2024 | August 2024
  
  Publication
- The Vision of Autonomic Computing: Can LLMs Make It a Reality?
  
  Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Jue Zhang, Qingwei Lin 林庆维, Gong Cheng, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  July 2024
  
  Preprint
- TaskWeaver: A Code-First Agent Framework
  
  Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  December 2023
  
  Publication
- Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets
  
  Fangkai Yang, Jue Zhang, Lu Wang, Bo Qiao, Di Weng, Xiaoting Qin, Gregory Weber, Durgesh Nandini Das, Srinivasan Rakhunathan, Ranganathan Srikanth, Qingwei Lin 林庆维, Dongmei Zhang
  
  2023 Knowledge Discovery and Data Mining | August 2023
  
  Publication
- Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
  
  Junjie Sheng, Lu Wang, Fangkai Yang, Bo Qiao, Hang Dong, Xiangfeng Wang, Bo Jin, Jun Wang, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW '23 | April 2023
  
  DOI
- NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365
  
  Lu Wang, Pu Zhao, Chao Du, Chuan Luo, Mengna Su, Fangkai Yang, Yudong Liu, Qingwei Lin 林庆维, Min Wang, Yingnong Dang, Hongyu Zhang, Saravan Rajmohan, Dongmei Zhang
  
  SIGKDD 2022 | August 2022
  
  Publication Project Project
- Spot Virtual Machine Eviction Prediction in Microsoft Cloud
  
  Fangkai Yang, Bowen Pang, Jue Zhang, Bo Qiao, Lu Wang, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Senthil Baladhandayutham, Victor Rühle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW'22 Companion | April 2022
  
  Publication
- Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
  
  Qibin Wang, Pu Zhao, Shaohan Huang, Fangkai Yang, Lu Wang, Furu Wei, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | August 2025, Vol abs/2509.00084
  
  DOI Publication Publication
- DUET: Joint Exploration of User Item Profiles in Recommendation System
  
  Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yi Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
  
  April 2026
  
  Publication
- UFO2: The Desktop AgentOS
  
  Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, Liqun Li, Yu Kang, Zhao Jiang, Suzhen Zheng, Rujia Wang, Jiaxu Qian, Ming-Jie Ma, Jianjun Lou, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | April 2025, Vol abs/2504.14603
  
  DOI Publication Publication Project Project
- ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
  
  Minghua He, Fangkai Yang, Pu Zhao, Wenjie Yin, Yu Kang, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.18460
  
  DOI Publication Publication Project
- Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
  
  Xing Zhang, Jiaheng Wen, Fangkai Yang, Pu Zhao, Yu Kang, Junhao Wang, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin 林庆维, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.16050
  
  DOI Publication Publication Project
- NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365
  
  Lu Wang, Pu Zhao, Chao Du, Chuan Luo, Mengna Su, Fangkai Yang, Yudong Liu, Qingwei Lin 林庆维, Min Wang, Yingnong Dang, Hongyu Zhang, Saravan Rajmohan, Dongmei Zhang
  
  SIGKDD 2022 | August 2022
  
  Publication Project Project
- Spot Virtual Machine Eviction Prediction in Microsoft Cloud
  
  Fangkai Yang, Bowen Pang, Jue Zhang, Bo Qiao, Lu Wang, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Senthil Baladhandayutham, Victor Rühle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW'22 Companion | April 2022
  
  Publication
- ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud
  
  Lu Wang, Mayukh Das, Fangkai Yang, Bo Qiao, Hang Dong, Si Qin, Victor Ruehle, Chetan Bansal, Eli Cortez, Íñigo Goiri, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  MLSys'25 | May 2025
  
  Publication
- UFO2: The Desktop AgentOS
  
  Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, Liqun Li, Yu Kang, Zhao Jiang, Suzhen Zheng, Rujia Wang, Jiaxu Qian, Ming-Jie Ma, Jianjun Lou, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | April 2025, Vol abs/2504.14603
  
  DOI Publication Publication Project Project
- COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty
  
  Lu Wang, Mayukh Das, Fangkai Yang, Chao Du, Bo Qiao, Hang Dong, Chetan Bansal, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang, Qi Zhang
  
  CIKM'24 | October 2024
  
  PDF
- Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-Demand VMs
  
  Fangkai Yang, Lu Wang, Zhenyu Xu, Jue Zhang, Liqun Li, Bo Qiao, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Terry Yang, Victor Ruehle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  ASPLOS'23 | March 2023
  
  Publication
- NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365
  
  Lu Wang, Pu Zhao, Chao Du, Chuan Luo, Mengna Su, Fangkai Yang, Yudong Liu, Qingwei Lin 林庆维, Min Wang, Yingnong Dang, Hongyu Zhang, Saravan Rajmohan, Dongmei Zhang
  
  SIGKDD 2022 | August 2022
  
  Publication Project Project
- Spot Virtual Machine Eviction Prediction in Microsoft Cloud
  
  Fangkai Yang, Bowen Pang, Jue Zhang, Bo Qiao, Lu Wang, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Senthil Baladhandayutham, Victor Rühle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW'22 Companion | April 2022
  
  Publication
- AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
  
  Xi Chen, Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Chao Du, Xi Cheng, Hangxin Liu, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  September 2024
  
  Preprint
- Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets
  
  Fangkai Yang, Jue Zhang, Lu Wang, Bo Qiao, Di Weng, Xiaoting Qin, Gregory Weber, Durgesh Nandini Das, Srinivasan Rakhunathan, Ranganathan Srikanth, Qingwei Lin 林庆维, Dongmei Zhang
  
  2023 Knowledge Discovery and Data Mining | August 2023
  
  Publication
- NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365
  
  Lu Wang, Pu Zhao, Chao Du, Chuan Luo, Mengna Su, Fangkai Yang, Yudong Liu, Qingwei Lin 林庆维, Min Wang, Yingnong Dang, Hongyu Zhang, Saravan Rajmohan, Dongmei Zhang
  
  SIGKDD 2022 | August 2022
  
  Publication Project Project
- Spot Virtual Machine Eviction Prediction in Microsoft Cloud
  
  Fangkai Yang, Bowen Pang, Jue Zhang, Bo Qiao, Lu Wang, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Senthil Baladhandayutham, Victor Rühle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW'22 Companion | April 2022
  
  Publication
- Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
  
  Junjie Sheng, Lu Wang, Fangkai Yang, Bo Qiao, Hang Dong, Xiangfeng Wang, Bo Jin, Jun Wang, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW '23 | April 2023
  
  DOI
- NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365
  
  Lu Wang, Pu Zhao, Chao Du, Chuan Luo, Mengna Su, Fangkai Yang, Yudong Liu, Qingwei Lin 林庆维, Min Wang, Yingnong Dang, Hongyu Zhang, Saravan Rajmohan, Dongmei Zhang
  
  SIGKDD 2022 | August 2022
  
  Publication Project Project
- Spot Virtual Machine Eviction Prediction in Microsoft Cloud
  
  Fangkai Yang, Bowen Pang, Jue Zhang, Bo Qiao, Lu Wang, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Senthil Baladhandayutham, Victor Rühle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW'22 Companion | April 2022
  
  Publication

- Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
  
  Qibin Wang, Pu Zhao, Shaohan Huang, Fangkai Yang, Lu Wang, Furu Wei, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | August 2025, Vol abs/2509.00084
  
  DOI Publication Publication
- UFO2: The Desktop AgentOS
  
  Chaoyun Zhang, He Huang, Chiming Ni, Jian Mu, Si Qin, Shilin He, Lu Wang, Fangkai Yang, Pu Zhao, Chao Du, Liqun Li, Yu Kang, Zhao Jiang, Suzhen Zheng, Rujia Wang, Jiaxu Qian, Ming-Jie Ma, Jianjun Lou, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  ArXiv | April 2025, Vol abs/2504.14603
  
  DOI Publication Publication Project Project
- ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
  
  Minghua He, Fangkai Yang, Pu Zhao, Wenjie Yin, Yu Kang, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.18460
  
  DOI Publication Publication Project
- Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
  
  Xing Zhang, Jiaheng Wen, Fangkai Yang, Pu Zhao, Yu Kang, Junhao Wang, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin 林庆维, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  ArXiv | January 2025, Vol abs/2501.16050
  
  DOI Publication Publication Project
- Enabling Autonomic Microservice Management through Self-Learning Agents
  
  Fenglin Yu, Fangkai Yang, Xiaoting Qin, Zhiyang Zhang, Jue Zhang, Qingwei Lin 林庆维, Hongyu Zhang, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  January 2025
  
  Preprint
- AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
  
  Xi Chen, Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Chao Du, Xi Cheng, Hangxin Liu, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
  
  September 2024
  
  Preprint
- The Vision of Autonomic Computing: Can LLMs Make It a Reality?
  
  Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Jue Zhang, Qingwei Lin 林庆维, Gong Cheng, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  July 2024
  
  Preprint
- DUET: Joint Exploration of User Item Profiles in Recommendation System
  
  Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yi Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
  
  April 2026
  
  Publication
- Beyond State Consistency: Behavior Consistency in Text-Based World Models
  
  Youling Huang, Guanqiao Chen, Junchi Yao, Lu Wang, Fangkai Yang, Chao Du, ChenZhuo Zhao, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
  
  April 2026
  
  Publication
- ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud
  
  Lu Wang, Mayukh Das, Fangkai Yang, Bo Qiao, Hang Dong, Si Qin, Victor Ruehle, Chetan Bansal, Eli Cortez, Íñigo Goiri, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  MLSys'25 | May 2025
  
  Publication
- Pretrain Value, Not Reward: Decoupled Value Policy Optimization
  
  Chenghua Huang, Lu Wang, Fangkai Yang, Pu Zhao, Zhixu Li, Qingwei Lin 林庆维, Dongmei Zhang, S. Rajmohan, Qi Zhang
  
  ICLR 2026 | February 2025
  
  Publication
- AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation
  
  Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin 林庆维, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  EMNLP'24 | November 2024
  
  Preprint
- COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty
  
  Lu Wang, Mayukh Das, Fangkai Yang, Chao Du, Bo Qiao, Hang Dong, Chetan Bansal, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang, Qi Zhang
  
  CIKM'24 | October 2024
  
  PDF
- Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
  
  Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin, Xiang Huang, Ling Chen, Qingwei Lin 林庆维, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
  
  ACL 2024 | August 2024
  
  Publication
- Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets
  
  Fangkai Yang, Jue Zhang, Lu Wang, Bo Qiao, Di Weng, Xiaoting Qin, Gregory Weber, Durgesh Nandini Das, Srinivasan Rakhunathan, Ranganathan Srikanth, Qingwei Lin 林庆维, Dongmei Zhang
  
  2023 Knowledge Discovery and Data Mining | August 2023
  
  Publication
- Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
  
  Junjie Sheng, Lu Wang, Fangkai Yang, Bo Qiao, Hang Dong, Xiangfeng Wang, Bo Jin, Jun Wang, Si Qin, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW '23 | April 2023
  
  DOI
- Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-Demand VMs
  
  Fangkai Yang, Lu Wang, Zhenyu Xu, Jue Zhang, Liqun Li, Bo Qiao, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Terry Yang, Victor Ruehle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  ASPLOS'23 | March 2023
  
  Publication
- NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365
  
  Lu Wang, Pu Zhao, Chao Du, Chuan Luo, Mengna Su, Fangkai Yang, Yudong Liu, Qingwei Lin 林庆维, Min Wang, Yingnong Dang, Hongyu Zhang, Saravan Rajmohan, Dongmei Zhang
  
  SIGKDD 2022 | August 2022
  
  Publication Project Project
- Spot Virtual Machine Eviction Prediction in Microsoft Cloud
  
  Fangkai Yang, Bowen Pang, Jue Zhang, Bo Qiao, Lu Wang, Camille Couturier, Chetan Bansal, Soumya Ram, Si Qin, Zhen Ma, Íñigo Goiri, Eli Cortez, Senthil Baladhandayutham, Victor Rühle, Saravan Rajmohan, Qingwei Lin 林庆维, Dongmei Zhang
  
  WWW'22 Companion | April 2022
  
  Publication
- TaskWeaver: A Code-First Agent Framework
  
  Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, Qingwei Lin 林庆维, Saravan Rajmohan, Dongmei Zhang
  
  December 2023
  
  Publication

Fangkai Yang

Publications

Beyond State Consistency: Behavior Consistency in Text-Based World Models

DUET: Joint Exploration of User Item Profiles in Recommendation System

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud

UFO2: The Desktop AgentOS

Pretrain Value, Not Reward: Decoupled Value Policy Optimization

ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation

Enabling Autonomic Microservice Management through Self-Learning Agents

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation

COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty

AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure

Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments

The Vision of Autonomic Computing: Can LLMs Make It a Reality?

TaskWeaver: A Code-First Agent Framework

Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning

Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-Demand VMs

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365

Spot Virtual Machine Eviction Prediction in Microsoft Cloud

DUET: Joint Exploration of User Item Profiles in Recommendation System

Beyond State Consistency: Behavior Consistency in Text-Based World Models

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud

UFO2: The Desktop AgentOS

Pretrain Value, Not Reward: Decoupled Value Policy Optimization

ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation

Enabling Autonomic Microservice Management through Self-Learning Agents

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation

COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty

AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure

Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments

The Vision of Autonomic Computing: Can LLMs Make It a Reality?

TaskWeaver: A Code-First Agent Framework

Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365

Spot Virtual Machine Eviction Prediction in Microsoft Cloud

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

DUET: Joint Exploration of User Item Profiles in Recommendation System

UFO2: The Desktop AgentOS

ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365

Spot Virtual Machine Eviction Prediction in Microsoft Cloud

ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud

UFO2: The Desktop AgentOS

COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty

Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-Demand VMs

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365

Spot Virtual Machine Eviction Prediction in Microsoft Cloud

AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure

Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365

Spot Virtual Machine Eviction Prediction in Microsoft Cloud

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365

Spot Virtual Machine Eviction Prediction in Microsoft Cloud

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

UFO2: The Desktop AgentOS

ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation

Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation

Enabling Autonomic Microservice Management through Self-Learning Agents

AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure

The Vision of Autonomic Computing: Can LLMs Make It a Reality?

DUET: Joint Exploration of User Item Profiles in Recommendation System

Beyond State Consistency: Behavior Consistency in Text-Based World Models

ProtoRAIL: A Risk-cognizant Imitation Agent for Adaptive vCPU Oversubscription In The Cloud

Pretrain Value, Not Reward: Decoupled Value Policy Optimization

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation

COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty

Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments

Contextual Self-attentive Temporal Point Process for Physical Decommissioning Prediction of Cloud Assets

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning

Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-Demand VMs

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365

Spot Virtual Machine Eviction Prediction in Microsoft Cloud