{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:10:57Z","timestamp":1777889457130,"version":"3.51.4"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306090,U24A20328"],"award-info":[{"award-number":["62306090,U24A20328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M764192"],"award-info":[{"award-number":["2024M764192"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00558","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5901-5911","source":"Crossref","is-referenced-by-count":1,"title":["Less is More: Empowering GUI Agent with Context-Aware Simplification"],"prefix":"10.1109","author":[{"given":"Gongwei","family":"Chen","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xurui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Shao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibo","family":"Lyu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiwen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinchuan","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bai","year":"2023","journal-title":"Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities"},{"key":"ref2","article-title":"Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation","volume-title":"The Thirteenth International Conference on Learning Representations, 2024","author":"Chae"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"ref7","author":"Christianos","year":"2023","journal-title":"Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"ref10","author":"Ge","year":"2024","journal-title":"Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining"},{"key":"ref11","author":"Gou","year":"2024","journal-title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref13","author":"Hu","year":"2024","journal-title":"iLLaVA: An Image is Worth Fewer Than 1\/3 Input Tokens in Large Multimodal Models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref15","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref16","article-title":"Star: Learning diverse robot skill abstractions through rotation-augmented vector quantization","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref17","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2925"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00308"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref22","author":"Li","year":"2025","journal-title":"Generative models in decision making: A survey"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1580"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00845"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01816"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/6814.001.0001"},{"key":"ref29","author":"Lu","year":"2024","journal-title":"GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.539"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1158"},{"key":"ref32","author":"Patel","year":"2024","journal-title":"Large Language Models Can SelfImprove At Web Agent Tasks"},{"key":"ref33","author":"Putta","journal-title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents"},{"key":"ref34","author":"Qi","year":"2024","journal-title":"WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning"},{"key":"ref35","author":"Qin","year":"2025","journal-title":"UI-TARS: Pioneering Automated GUI Interaction with Native Agents"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2609"},{"key":"ref37","author":"Shang","year":"2024","journal-title":"LlaVA- PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01026"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367749"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1330"},{"key":"ref42","article-title":"What does CLIP know about a red circle?","author":"Shtedritski","year":"2023","journal-title":"Visual prompt engineering for VLMs"},{"key":"ref43","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0088"},{"key":"ref45","author":"Wang","year":"2024","journal-title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception"},{"key":"ref46","author":"Wang","year":"2024","journal-title":"Qwen2-VL: Enhancing Vision-Language Model\u2019s Perception of the World at Any Resolution"},{"key":"ref47","author":"Wang","year":"2024","journal-title":"GUI Agents with Foundation Models: A Comprehensive Survey"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3511593"},{"key":"ref49","author":"Zhiruo Wang","year":"2024","journal-title":"Agent Workflow Memory"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649379"},{"key":"ref51","author":"Wen","year":"2024","journal-title":"DroidBot-GPT: GPT-powered UI Automation for Android"},{"key":"ref52","author":"Wen","year":"2024","journal-title":"Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers"},{"key":"ref53","author":"Wu","year":"2024","journal-title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.282"},{"key":"ref55","author":"Xu","year":"2024","journal-title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction"},{"key":"ref56","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models","author":"Yao","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02777"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713600"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02184"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.186"},{"key":"ref62","author":"Zhang","year":"2024","journal-title":"MMInA: Benchmarking Multihop Multimodal Internet Agents"},{"key":"ref63","author":"Zheng","year":"2024","journal-title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445185.pdf?arnumber=11445185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:13:06Z","timestamp":1777612386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00558","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}