{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:37:57Z","timestamp":1776357477844,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2026"],"award-info":[{"award-number":["U23B2026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China","award":["62372305"],"award-info":[{"award-number":["62372305"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024B1515040012"],"award-info":[{"award-number":["2024B1515040012"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20230923114809020"],"award-info":[{"award-number":["KJZD20230923114809020"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,4]]},"DOI":"10.1145\/3798065.3798072","type":"proceedings-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T19:30:21Z","timestamp":1775676621000},"page":"43-49","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DRLLMS: Network-Adaptive Reasoning Control for Interactive LLM Streaming"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1766-3755","authenticated-orcid":false,"given":"Tao","family":"Lyu","sequence":"first","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9439-6725","authenticated-orcid":false,"given":"Cong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6438-3790","authenticated-orcid":false,"given":"Haihan","family":"Duan","sequence":"additional","affiliation":[{"name":"Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1706-5957","authenticated-orcid":false,"given":"Xiaoyi","family":"Fan","sequence":"additional","affiliation":[{"name":"Jiangxing Intelligence Inc., Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-699X","authenticated-orcid":false,"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1991-290X","authenticated-orcid":false,"given":"Laizhong","family":"Cui","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning. ArXiv abs\/2503.04697","author":"Aggarwal Pranjal","year":"2025","unstructured":"Pranjal Aggarwal and Sean Welleck. 2025. L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning. ArXiv abs\/2503.04697 (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2025.100143"},{"key":"e_1_3_2_1_3_1","volume-title":"Length Instruction Fine-Tuning with Chain-of-Thought (LIFT-COT): Enhancing Length Control and Reasoning in Edge-Deployed Large Language Models. Electronics","author":"Chen Pinzhe","year":"2025","unstructured":"Pinzhe Chen and Zhen Li. 2025. Length Instruction Fine-Tuning with Chain-of-Thought (LIFT-COT): Enhancing Length Control and Reasoning in Edge-Deployed Large Language Models. Electronics (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Optimizing Length Compression in Large Reasoning Models. ArXiv abs\/2506.14755","author":"Cheng Zhengxiang","year":"2025","unstructured":"Zhengxiang Cheng, Dongping Chen, Mingyang Fu, and Tianyi Zhou. 2025. Optimizing Length Compression in Large Reasoning Models. ArXiv abs\/2506.14755 (2025)."},{"key":"e_1_3_2_1_5_1","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_6_1","volume-title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems. In Annual Meeting of the Association for Computational Linguistics.","author":"He Chaoqun","year":"2024","unstructured":"Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, and Maosong Sun. 2024. OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems. In Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_7_1","volume-title":"Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS (2021)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_9_1","volume-title":"SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning. ArXiv abs\/2505.11274","author":"Li Zheng","year":"2025","unstructured":"Zheng Li, Qingxiu Dong, Jingyuan Ma, Di Zhang, and Zhifang Sui. 2025. SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning. ArXiv abs\/2505.11274 (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"Let's Verify Step by Step. arXiv preprint arXiv:2305.20050","author":"Lightman Hunter","year":"2023","unstructured":"Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let's Verify Step by Step. arXiv preprint arXiv:2305.20050 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services. ArXiv abs\/2404.16283","author":"Liu Jiachen","year":"2024","unstructured":"Jiachen Liu, Zhiyu Wu, Jae-Won Chung, Fan Lai, Myungjin Lee, and Mosharaf Chowdhury. 2024. Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services. ArXiv abs\/2404.16283 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning. ArXiv abs\/2501.12570","author":"Luo Haotian","year":"2025","unstructured":"Haotian Luo, Li Shen, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Naiqiang Tan, Xiaochun Cao, and Dacheng Tao. 2025. O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning. ArXiv abs\/2501.12570 (2025)."},{"key":"e_1_3_2_1_13_1","volume-title":"Raluca Ada Popa, and Ion Stoica.","author":"Luo Michael","year":"2025","unstructured":"Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y. Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica. 2025. DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL. Notion Blog. https:\/\/pretty-radio-b75.notion.site\/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2"},{"key":"e_1_3_2_1_14_1","volume-title":"Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching. ArXiv abs\/2503.05248","author":"Pang Bowen","year":"2025","unstructured":"Bowen Pang, Kai Li, and Feifan Wang. 2025. Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching. ArXiv abs\/2503.05248 (2025)."},{"key":"e_1_3_2_1_15_1","volume-title":"DeepSeek-Math: Pushing the Limits of Mathematical Reasoning in Open Language Models. ArXiv abs\/2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Jun-Mei Song, Mingchuan Zhang, Y. K. Li, Yu Wu, and Daya Guo. 2024. DeepSeek-Math: Pushing the Limits of Mathematical Reasoning in Open Language Models. ArXiv abs\/2402.03300 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Hybrid-Flow: A Flexible and Efficient RLHF Framework. arXiv preprint arXiv: 2409.19256","author":"Sheng Guangming","year":"2024","unstructured":"Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2024. Hybrid-Flow: A Flexible and Efficient RLHF Framework. arXiv preprint arXiv: 2409.19256 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards. ArXiv abs\/2505.18298","author":"Su Jinyan","year":"2025","unstructured":"Jinyan Su and Claire Cardie. 2025. Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards. ArXiv abs\/2505.18298 (2025)."},{"key":"e_1_3_2_1_18_1","unstructured":"Qwen Team. 2025. QwQ-32B: Embracing the Power of Reinforcement Learning. https:\/\/qwenlm.github.io\/blog\/qwq-32b\/"},{"key":"e_1_3_2_1_19_1","volume-title":"Wenjie Wang, and Wenjie Li.","author":"Xia Heming","year":"2025","unstructured":"Heming Xia, Yongqi Li, Chak Tou Leong, Wenjie Wang, and Wenjie Li. 2025. TokenSkip: Controllable Chain-of-Thought Compression in LLMs. ArXiv abs\/2502.12067 (2025)."},{"key":"e_1_3_2_1_20_1","volume-title":"Scalable Chain of Thoughts via Elastic Reasoning. ArXiv abs\/2505.05315","author":"Xu Yuhui","year":"2025","unstructured":"Yuhui Xu, Hanze Dong, Lei Wang, Doyen Sahoo, Junnan Li, and Caiming Xiong. 2025. Scalable Chain of Thoughts via Elastic Reasoning. ArXiv abs\/2505.05315 (2025)."},{"key":"e_1_3_2_1_21_1","volume-title":"arXiv preprint arXiv:2412.15115","author":"Yang An","year":"2024","unstructured":"An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tianyi Tang, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, and Zihan Qiu. 2024. Qwen2.5 Technical Report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts. ArXiv abs\/2508.00234","author":"Yang Jin","year":"2025","unstructured":"Jin Yang, Qiong Wu, Zhiying Feng, Zhi Zhou, Deke Guo, and Xu Chen. 2025. Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts. ArXiv abs\/2508.00234 (2025)."}],"event":{"name":"NOSSDAV '26: ACM Multimedia Systems Conference 2026","location":"Hong Kong Hong Kong","acronym":"NOSSDAV '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 36th Workshop on Network and Operating System Support for Digital Audio and Video"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3798065.3798072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:32:45Z","timestamp":1776353565000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3798065.3798072"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":22,"alternative-id":["10.1145\/3798065.3798072","10.1145\/3798065"],"URL":"https:\/\/doi.org\/10.1145\/3798065.3798072","relation":{},"subject":[],"published":{"date-parts":[[2026,4,4]]},"assertion":[{"value":"2026-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}