Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key.

Xinpeng Wei

Tianle Wang 0009 Zhaoyang Wang 0004 Guangchen Lan Xinpeng Wei Sipeng Zhang Guanwen Qiu Abulhair Saparov Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key. 2026 May abs/2605.06638 CoRR https://doi.org/10.48550/arXiv.2605.06638 db/journals/corr/corr2605.html#abs-2605-06638 streams/journals/corr

Yihang Chen Pin Qian Su Wang Sipeng Zhang Huan Xu Shuhuai Lin Xinpeng Wei Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict. 2026 May abs/2605.14473 CoRR https://doi.org/10.48550/arXiv.2605.14473 db/journals/corr/corr2605.html#abs-2605-14473 streams/journals/corr

Jian Xie Tianhe Lin Zilu Wang Yuting Ning Yuekun Yao Tianci Xue Zhehao Zhang Zhongyang Li Kai Zhang 0033 Yufan Wu Shijie Chen Boyu Gou Mingzhe Han Yifei Wang Vint Lee Xinpeng Wei Xiangjun Wang Yu Su 0001 Huan Sun 0001 QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks. 2026 May abs/2605.24218 CoRR https://doi.org/10.48550/arXiv.2605.24218 db/journals/corr/corr2605.html#abs-2605-24218 streams/journals/corr

Pin Qian Su Wang Xiaoyuan Wang Yihang Chen Wenxuan Xu Qiaolin Yu Shuhuai Lin Sipeng Zhang Junxian You Xinpeng Wei Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG. 2026 May abs/2605.28044 CoRR https://doi.org/10.48550/arXiv.2605.28044 db/journals/corr/corr2605.html#abs-2605-28044 streams/journals/corr

Guangchen Lan Sipeng Zhang Tianle Wang 0009 Yuwei Zhang Daoan Zhang Xinpeng Wei Xiaoman Pan Hongming Zhang 0009 Dong-Jun Han Christopher G. Brinton MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge. 2025 July abs/2507.21183 CoRR https://doi.org/10.48550/arXiv.2507.21183 db/journals/corr/corr2507.html#abs-2507-21183 streams/journals/corr

Xinpeng Wei Zhichao Li Cheng Tan 0005 Optimizing GPU Sharing for Container-Based DNN Serving with Multi-Instance GPUs. 68-82 2024 SYSTOR https://doi.org/10.1145/3688351.3689156 https://www.wikidata.org/entity/Q131011704 conf/systor/2024 db/conf/systor/systor2024.html#WeiL024

Zitong Zhan Huan Xu Zihang Fang Xinpeng Wei Yaoyu Hu Chen Wang 0033 Bundle Adjustment in the Eager Mode. 2024 abs/2409.12190 CoRR https://doi.org/10.48550/arXiv.2409.12190 db/journals/corr/corr2409.html#abs-2409-12190 streams/journals/corr

Cheng Chen Xinpeng Wei Wang Guo Cheng Peng Qingxue Li Knowledge service technology of soil testing formula based on the integration of knowledge map and location service. 600-604 2022 CSSE https://doi.org/10.1145/3569966.3570118 conf/csse/2022 db/conf/csse/csse2022.html#ChenWGPL22

Xinpeng Wei Daoru Han Xiaoping Du Physics-Based Gaussian Process Method for Predicting Average Product Lifetime in Design Stage. 2021 21 J. Comput. Inf. Sci. Eng. 4 https://doi.org/10.1115/1.4049509 db/journals/jcise/jcise21.html#WeiHD21

Gao Zheng 0001 Ning Wang 0001 Rahim Tafazolli Xinpeng Wei Jinze Yang Virtual Data-Plane Addressing for SDN-based Space and Terrestrial Network Integration. 1-6 2021 HPSR https://doi.org/10.1109/HPSR52026.2021.9481837 conf/hpsr/2021 db/conf/hpsr/hpsr2021.html#ZhengWTWY21 Miquel Ferriol-Galmés Roger Coll Aumatell Albert Cabellos-Aparicio Shoushou Ren Xinpeng Wei Bingyang Liu Preventing Route Leaks using a Decentralized Approach: An Experimental Evaluation. 1-6 2020 ICNP https://doi.org/10.1109/ICNP49622.2020.9259367 conf/icnp/2020 db/conf/icnp/icnp2020.html#GalmesACRWL20 Gao Zheng 0001 Ning Wang 0001 Rahim Tafazolli Xinpeng Wei Geosynchronous Network Grid Addressing for Integrated Space-Terrestrial Networks. 1-6 2020 ICNP https://doi.org/10.1109/ICNP49622.2020.9259376 conf/icnp/2020 db/conf/icnp/icnp2020.html#ZhengWTW20 Stefano Angieri Marcelo Bagnulo Alberto García-Martínez Bingyang Liu Xinpeng Wei InBlock4: Blockchain-based Route Origin Validation. 291-296 2020 INFOCOM Workshops https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162879 conf/infocom/2020w db/conf/infocom/infocom2020w.html#AngieriBGLW20 Khalil Saadat Ning Wang 0001 Xinpeng Wei Bin Da Rahim Tafazolli Reconfigurable Blockchains for Dynamic Cluster-based Applications. 925-931 2020 ISPA/BDCloud/SocialCom/SustainCom https://doi.org/10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00142 conf/ispa/2020 db/conf/ispa/ispa2020.html#SaadatWWDT20 Miquel Ferriol-Galmés Roger Coll Aumatell Albert Cabellos-Aparicio Shoushou Ren Xinpeng Wei Bingyang Liu Preventing Route Leaks using a Decentralized Approach. 509-513 2020 Networking https://ieeexplore.ieee.org/document/9142712 conf/networking/2020 db/conf/networking/networking2020.html#GalmesACRWL20

H. Anthony Chan Xinpeng Wei Jong-Hyouk Lee Seil Jeon Carlos J. Bernardos Distributed Mobility Anchoring. 2020 1-18 RFC 8818 October https://doi.org/10.17487/RFC8818 https://www.wikidata.org/entity/Q102151226 db/journals/rfc/rfc8800-8899.html

Teng Fang Chao Jiang 0005 Zhi Liang Huang Xinpeng Wei Xu Han 0011 Time-Variant Reliability-Based Design Optimization Using an Equivalent Most Probable Point. 175-186 2019 68 IEEE Trans. Reliab. 1 https://doi.org/10.1109/TR.2018.2823737 db/journals/tr/tr68.html#FangJHWH19

Shoushou Ren Bingyang Liu Fei Yang Xinpeng Wei Xue Yang Chuang Wang 0012 BlockDNS: Enhancing Domain Name Ownership and Data Authenticity with Blockchain. 1-6 2019 GLOBECOM https://doi.org/10.1109/GLOBECOM38437.2019.9013817 conf/globecom/2019 db/conf/globecom/globecom2019.html#RenLYWYW19

Changqiao Xu Peng Wang 0071 Chunshan Xiong Xinpeng Wei Gabriel-Miro Muntean Pipeline Network Coding-Based Multipath Data Transfer in Heterogeneous Wireless Networks. 376-390 2017 63 IEEE Trans. Broadcast. 2 https://doi.org/10.1109/TBC.2016.2590819 db/journals/tbc/tbc63.html#XuWXWM17

Zhi Liang Huang Chao Jiang 0005 Xiao Ming Li Xinpeng Wei Teng Fang Xu Han 0011 A Single-Loop Approach for Time-Variant Reliability-Based Design Optimization. 651-661 2017 66 IEEE Trans. Reliab. 3 https://doi.org/10.1109/TR.2017.2703593 db/journals/tr/tr66.html#HuangJLWFH17

H. Anthony Chan Xinpeng Wei Jong-Hyouk Lee Fred L. Templin Seil Jeon A systematic classification of distributed IP mobility. 455-460 2016 INFOCOM Workshops https://doi.org/10.1109/INFCOMW.2016.7562120 conf/infocom/2016w db/conf/infocom/infocom2016w.html#ChanWLTJ16 Yi Lin Xiangyang Gong Wendong Wang 0003 Xinpeng Wei Lei Zhu Tunnel Congestion Exposure and Feedback. 551-554 2013 DASC https://doi.org/10.1109/DASC.2013.123 https://doi.ieeecomputersociety.org/10.1109/DASC.2013.123 conf/dasc/2013 db/conf/dasc/dasc2013.html#LinGWWZ13 Stefano Angieri Roger Coll Aumatell Marcelo Bagnulo Carlos J. Bernardos Christopher G. Brinton Albert Cabellos-Aparicio H. Anthony Chan Cheng Chen Shijie Chen Yihang Chen Bin Da Xiaoping Du Teng Fang Zihang Fang Miquel FerriolMiquel Ferriol-Galmés Alberto García-Martínez Xiangyang Gong Boyu Gou Wang Guo Daoru Han Dong-Jun Han Mingzhe Han Xu Han 0011 Yaoyu Hu Zhi Liang Huang Seil Jeon Chao Jiang 0005 Guangchen Lan Jong-Hyouk Lee Vint Lee Qingxue Li Xiaoming LiXiao Ming Li Zhichao Li Zhongyang Li Shuhuai Lin Tianhe Lin Yi Lin Bingyang Liu Gabriel-Miro Muntean Yuting Ning Xiaoman Pan Cheng Peng Pin Qian Guanwen Qiu Shoushou Ren Khalil Saadat Abulhair Saparov Yu Su 0001 Huan Sun 0001 Rahim Tafazolli Cheng Tan 0005 Fred L. Templin Chen Wang 0033 Chuang Wang 0012 Ning Wang 0001 Peng Wang 0071 Su Wang Tianle Wang 0009 Wendong Wang 0003 Xiangjun Wang Xiaoyuan Wang Yifei Wang Zhaoyang Wang 0004 Zilu Wang Yufan Wu Jian Xie Chunshan Xiong Changqiao Xu Huan Xu Wenxuan Xu Tianci Xue Fei Yang Jinze Yang Xue Yang Yuekun Yao Junxian You Qiaolin Yu Zitong Zhan Daoan Zhang Hongming Zhang 0009 Kai Zhang 0033 Sipeng Zhang Yuwei Zhang Zhehao Zhang Gao Zheng 0001 Lei Zhu