{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:11:56Z","timestamp":1788844316246,"version":"build-2803163510"},"reference-count":35,"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":["62302048,U25A20436,62272050"],"award-info":[{"award-number":["62302048,U25A20436,62272050"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/icws72778.2026.00092","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:16:57Z","timestamp":1788808617000},"page":"735-744","source":"Crossref","is-referenced-by-count":0,"title":["ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services"],"prefix":"10.1109","author":[{"given":"Kuan","family":"Yan","sequence":"first","affiliation":[{"name":"Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqing","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"ref4","article-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection","volume-title":"The Twelfth International Conference on Learning Representations","author":"Asai","year":"2024"},{"key":"ref5","article-title":"Search-r1: Training llms to reason and leverage search engines with reinforcement learning","author":"Jin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3562362"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2026.3656318"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00105"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2026.3665250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tsc.2025.3611379"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2026.3656632"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0722"},{"key":"ref16","article-title":"In-context autoencoder for context compression in a large language model","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ge","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3476"},{"key":"ref19","article-title":"Recomp: Improving retrieval-augmented lms with compression and selective augmentation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu","year":"2024"},{"key":"ref20","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.276"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1073"},{"key":"ref29","article-title":"Rat: Retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.365"},{"key":"ref31","article-title":"Inftythink: Breaking the length limits of long-context reasoning in large language models","author":"Yan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICC51166.2024.10622991"},{"key":"ref33","article-title":"Ultrarag: A low-code mcp framework for building complex and innovative rag pipelines","volume-title":"OpenBMB","year":"2025"},{"key":"ref34","article-title":"Api pricing","year":"2026","journal-title":"OpenAI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3724420"}],"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\/11670192.pdf?arnumber=11670192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:53:45Z","timestamp":1788843225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00092","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}