{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:12:07Z","timestamp":1788844327693,"version":"build-2803163510"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62273089"],"award-info":[{"award-number":["62273089"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/icws72778.2026.00108","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:08:57Z","timestamp":1788808137000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["CompQ: QoE-Aware Compensation for Resumed Requests in Interactive LLM Inference Services"],"prefix":"10.1109","author":[{"given":"Yinming","family":"Tan","sequence":"first","affiliation":[{"name":"Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Di","sequence":"additional","affiliation":[{"name":"Zhejiang Normal University","place":["Jinhua, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pan","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Normal University","place":["Jinhua, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Toolllm: Facilitating large language models to master 16000+ real-world apis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qin","year":"2024"},{"key":"ref2","volume-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2024"},{"key":"ref3","article-title":"Agentboard: An analytical evaluation board of multi-turn LLM agents","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024","author":"Ma","year":"2024"},{"key":"ref4","volume-title":"Nalar: An agent serving framework","author":"Laju","year":"2026"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764814"},{"key":"ref6","volume-title":"Andes: Defining and enhancing quality-of-experience in llm-based text streaming services","author":"Liu","year":"2024"},{"key":"ref7","article-title":"Infercept: Efficient intercept support for augmented large language model inference","volume-title":"Forty-first International Conference on Machine Learning, Vienna, Austria","author":"Abhyankar","year":"2024"},{"key":"ref8","volume-title":"Continuum: Efficient and robust multi-turn llm agent scheduling with kv cache time-to-live","author":"Li","year":"2026"},{"key":"ref9","volume-title":"Concur: High-throughput agentic batch inference of 1lm via congestion-based concurrency control","author":"Chen","year":"2026"},{"key":"ref10","first-page":"965","article-title":"Fairness in serving large language models","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Sheng","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2000"},{"key":"ref12","volume-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref13","volume-title":"Sharegpt vicuna unfiltered: Cleaned split dataset","year":"2023"},{"key":"ref14","first-page":"205","article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","volume-title":"2020 USENIX annual technical conference (USENIX ATC 20)","author":"Shahrad","year":"2020"},{"key":"ref15","volume-title":"Thunderagent: A simple, fast and program-aware agentic inference system","author":"Kang","year":"2026"},{"key":"ref16","volume-title":"Autellix: An efficient serving engine for llm agents as general programs","author":"Luo","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00120"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref19","volume-title":"Fast distributed inference serving for large language models","author":"Wu","year":"2024"},{"key":"ref20","first-page":"193","article-title":"\\{DistServe\\}: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong","year":"2024"},{"key":"ref21","first-page":"117","article-title":"Taming \\{Throughput-Latency\\} tradeoff in \\{LLM\\} inference with \\{Sarathi-Serve\\}","volume-title":"18th USENIX symposium on operating systems design and implementation (OSDI 24)","author":"Agrawal","year":"2024"},{"key":"ref22","volume-title":"Justitia: Fair and efficient scheduling of task-parallel llm agents with selective pampering","author":"Yang","year":"2026"},{"key":"ref23","volume-title":"Ensuring fair llm serving amid diverse applications","author":"Khan","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00105"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS60048.2023.00094"}],"event":{"name":"2026 IEEE International Conference on Web Services (ICWS)","location":"Sydney, Australia","start":{"date-parts":[[2026,7,13]]},"end":{"date-parts":[[2026,7,18]]}},"container-title":["2026 IEEE International Conference on Web Services (ICWS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11670018\/11670022\/11670162.pdf?arnumber=11670162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:53:33Z","timestamp":1788843213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00108","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}