{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T06:29:08Z","timestamp":1786602548691,"version":"build-2736575974"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/icde65706.2026.00134","type":"proceedings-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T19:13:44Z","timestamp":1786562024000},"page":"1759-1772","source":"Crossref","is-referenced-by-count":0,"title":["HEXGEN-FLOW: Optimizing LLM Inference Request Scheduling for Agentic Text-to-SQL"],"prefix":"10.1109","author":[{"given":"You","family":"Peng","sequence":"first","affiliation":[{"name":"HKUST","place":["Hong Kong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youhe","family":"Jiang","sequence":"additional","affiliation":[{"name":"HKUST","place":["Hong Kong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqi","family":"Jiang","sequence":"additional","affiliation":[{"name":"ETH Zurich","place":["Zurich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binhang","family":"Yuan","sequence":"additional","affiliation":[{"name":"HKUST","place":["Hong Kong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.14778\/3641204.3641221"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682003"},{"key":"ref3","article-title":"Dr. spider: A diagnostic evaluation benchmark towards text-to-sql robustness","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583165"},{"key":"ref5","volume-title":"Openai gpt-4o","year":"2024"},{"key":"ref6","author":"Reid","year":"2024","journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context"},{"key":"ref7","volume-title":"The claude 3 model family: Opus, sonnet, haiku","year":"2024"},{"key":"ref8","author":"Jiang","year":"2024","journal-title":"Mixtral of experts"},{"key":"ref9","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref10","author":"Snell","year":"2024","journal-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters"},{"key":"ref11","author":"Brown","year":"2024","journal-title":"Large language monkeys: Scaling inference compute with repeated sampling"},{"key":"ref12","volume-title":"Nvidia reinvents computer graphics with turing architecture","year":"2018"},{"key":"ref13","volume-title":"Nvidia\u2019s new ampere data center gpu in full production","year":"2020"},{"key":"ref14","volume-title":"Nvidia announces hopper architecture, the next generation of accelerated computing","year":"2022"},{"key":"ref15","volume-title":"Nvidia blackwell platform arrives to power a new era of computing","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698523"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698523"},{"key":"ref21","volume-title":"Revisiting slo and goodput metrics in llm serving","author":"Wang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3721146.3721947"},{"key":"ref23","author":"Talaei","year":"2024","journal-title":"Chess: Contextual harnessing for efficient sql synthesis"},{"key":"ref24","volume-title":"Text generation inference","year":"2023"},{"key":"ref25","volume-title":"Tensorrt-1lm","year":"2023"},{"key":"ref26","first-page":"521","article-title":"Orca: A distributed serving system for \\{Transformer-Based\\} generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu","year":"2022"},{"key":"ref27","volume-title":"Nvidia triton inference server","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707215"},{"key":"ref29","first-page":"21 946","article-title":"Hexgen: Generative inference of large language model over heterogeneous environment","volume-title":"International Conference on Machine Learning. PMLR","author":"Jiang","year":"2024"},{"key":"ref30","author":"Jiang","year":"2025","journal-title":"Hexgen-2: Disaggregated generative inference of llms in heterogeneous environment"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4725-4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2859"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.1998.726348"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC65282.2025.11059653"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1835"},{"key":"ref36","first-page":"540","article-title":"Mac-sql: A multi-agent collaborative framework for text-to-sql","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Wang"},{"key":"ref37","author":"Yang","year":"2025","journal-title":"Qwen3 technical report"},{"key":"ref38","first-page":"3911","article-title":"Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Yu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-006-7419-9"},{"key":"ref40","doi-asserted-by":"crossref","volume-title":"Load balancing guardrails: Keeping your heavy traffic on the road to low response times","author":"Grosof","DOI":"10.1145\/3309697.3331514"},{"key":"ref41","article-title":"Ray Serve: Scalable and Programmable Serving","year":"2026","journal-title":"Online documentation (Ray Serve)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539795288490"},{"key":"ref43","first-page":"663","article-title":"\\{AlpaServe\\}: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li","year":"2023"},{"key":"ref44","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":"ref45","volume-title":"A quantitative measure of fairness and discrimination for resource allocation in shared computer systems","author":"Jain","year":"2026"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-022-00776-8"},{"issue":"2","key":"ref47","first-page":"1","article-title":"Fewshot text-to-sql translation using structure and content prompt learning","volume-title":"Proceedings of the ACM on Management of Data","volume":"1","author":"Gu","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3654930"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3681960"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.481"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1577"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.14778\/3659437.3659452"},{"key":"ref54","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.910"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.350"},{"key":"ref57","first-page":"9793","article-title":"Solid-sql: Enhanced schema-linking based in-context learning for robust text-to-sql","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Liu","year":"2025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1882"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3725394"},{"key":"ref60","author":"Ao","year":"2025","journal-title":"Optimizing llm inference: Fluid-guided online scheduling with memory constraints"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716011"},{"key":"ref62","author":"Borui","year":"2025","journal-title":"Efficient llm serving on hybrid real-time and best-effort requests"},{"key":"ref63","first-page":"173","article-title":"Llumnix: Dynamic scheduling for large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Sun","year":"2024"},{"key":"ref64","author":"Fang","year":"2025","journal-title":"Improving the end-toend efficiency of offline inference for multi-11m applications based on sampling and simulation"}],"event":{"name":"2026 IEEE 42nd International Conference on Data Engineering (ICDE)","location":"Montreal, QC, Canada","start":{"date-parts":[[2026,5,4]]},"end":{"date-parts":[[2026,5,8]]}},"container-title":["2026 IEEE 42nd International Conference on Data Engineering (ICDE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11629178\/11629165\/11629392.pdf?arnumber=11629392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T06:01:50Z","timestamp":1786600910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11629392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icde65706.2026.00134","relation":{},"subject":[],"published":{"date-parts":[[2026,5]]}}}