{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:46:42Z","timestamp":1782798402094,"version":"3.54.5"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571499","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent System for Orchestrating Retrieval and Multimodal Reasoning in Cloud Environments"],"prefix":"10.1109","author":[{"given":"Shuo","family":"Yang","sequence":"first","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinran","family":"Zheng","sequence":"additional","affiliation":[{"name":"University College London,London,United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinfeng","family":"Xu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinze","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zewei","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edith C. H.","family":"Ngai","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3158253"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3624478"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26752"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ject.2024.08.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/890"},{"key":"ref6","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3646"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.63317\/39sysjo27vbh"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0623"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3428972"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3382"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp55912.2026.11460996"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591629"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651504"},{"key":"ref15","article-title":"Single-agent or multi-agent systems? why not both?","author":"Gao","year":"2025"},{"key":"ref16","article-title":"Which agent causes task failures and when? on automated failure attribution of llm multi-agent systems","author":"Zhang","year":"2025"},{"key":"ref17","article-title":"Gptswarm: Language agents as optimizable graphs","volume-title":"Forty-first International Conference on Machine Learning","author":"Zhuge"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.296"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s44336-024-00009-2"},{"key":"ref21","article-title":"Internet of agents: Weaving a web of heterogeneous agents for collaborative intelligence","author":"Chen","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3409051"},{"key":"ref23","article-title":"Autoagents: A framework for automatic agent generation","author":"Chen","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2522"},{"key":"ref25","article-title":"Llm-based multi-agent systems: Techniques and business perspectives","author":"Yang","year":"2024"},{"key":"ref26","article-title":"Scaling large language model-based multi-agent collaboration","author":"Qian","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.259"},{"key":"ref28","article-title":"On the resilience of llm-based multi-agent collaboration with faulty agents","volume-title":"Forty-second International Conference on Machine Learning","author":"Huang"},{"key":"ref29","article-title":"Llm multi-agent systems: Challenges and open problems","author":"Han","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698525"},{"key":"ref31","article-title":"Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning","author":"Wang","year":"2024"},{"key":"ref32","article-title":"Perception, reason, think, and plan: A survey on large multimodal reasoning models","author":"Li","year":"2025"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref36","article-title":"Qwen3-vl technical report","author":"Bai","year":"2025"},{"key":"ref37","article-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2584"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0939"},{"key":"ref40","article-title":"Position: Multimodal large language models can significantly advance scientific reasoning","author":"Yan","year":"2025"},{"key":"ref41","article-title":"Multimodal chain-of-thought reasoning: A comprehensive survey","author":"Wang","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591879"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758307"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.609"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.499"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651910"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2025.3553939"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i4.37249"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714748"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01240"},{"key":"ref51","article-title":"E2lvlm: Evidence-enhanced large vision-language model for multimodal out-of-context misinformation detection","author":"Wu","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3774905.3796483"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.545"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47436-2_27"},{"issue":"6","key":"ref55","article-title":"Detecting out-of-context multimodal misinformation with interpretable neural-symbolic model","volume":"2","author":"Zhang","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.22"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571499.pdf?arnumber=11571499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:38:36Z","timestamp":1782797916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571499","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}