{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:42Z","timestamp":1766061642616,"version":"3.48.0"},"reference-count":73,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246582","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"14939-14946","source":"Crossref","is-referenced-by-count":0,"title":["GraspMAS: Zero-Shot Language-driven Grasp Detection with Multi-Agent System"],"prefix":"10.1109","author":[{"given":"Quang","family":"Nguyen","sequence":"first","affiliation":[{"name":"FPT Software AI Center,Vietnam"}]},{"given":"Tri","family":"Le","sequence":"additional","affiliation":[{"name":"FPT Software AI Center,Vietnam"}]},{"given":"Huy","family":"Nguyen","sequence":"additional","affiliation":[{"name":"TU,Automation & Control Institute (ACIN),Wien,Austria"}]},{"given":"Thieu","family":"Vo","sequence":"additional","affiliation":[{"name":"NUS,Department of Mathematics,Singapore"}]},{"given":"Tung D.","family":"Ta","sequence":"additional","affiliation":[{"name":"University of Tokyo,Department of Creative Informatics,Japan"}]},{"given":"Baoru","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}]},{"given":"Minh N.","family":"Vu","sequence":"additional","affiliation":[{"name":"TU,Automation & Control Institute (ACIN),Wien,Austria"}]},{"given":"Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Computer Science,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-020-00021-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/mti2030057"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759156"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01695"},{"article-title":"Language-guided robot grasping: Clip-based referring grasp synthesis in clutter","year":"2023","author":"Tziafas","key":"ref9"},{"key":"ref10","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeuRIPS"},{"year":"2023","key":"ref11","article-title":"Gpt-4 technical report"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref12"},{"article-title":"Deepseek-v3 technical report","year":"2024","author":"Liu","key":"ref13"},{"key":"ref14","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2023","journal-title":"CoRL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref17","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2023","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10802256"},{"key":"ref21","article-title":"Cliport: What and where pathways for robotic manipulation","author":"Shridhar","year":"2022","journal-title":"CoRL"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611277"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320012"},{"key":"ref27","article-title":"Towards open-world grasping with large vision-language models","author":"Tziafas","year":"2024","journal-title":"CoRL"},{"key":"ref28","article-title":"Thinkgrasp: A vision-language system for strategic part grasping in clutter","author":"Qian","year":"2024","journal-title":"CoRL"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref30","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","author":"Lu","year":"2024","journal-title":"NeuRIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"article-title":"Robocoder: Robotic learning from basic skills to general tasks with large language models","year":"2024","author":"Li","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01543"},{"key":"ref35","article-title":"Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents","author":"Wang","year":"2023","journal-title":"NeuRIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509439"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907124"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9402-3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811367"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561994"},{"article-title":"Reasoning grasping via multi-modal large language model","year":"2024","author":"Jin","key":"ref45"},{"article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","year":"2023","author":"Bubeck","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"article-title":"Craft: Customizing llms by creating and retrieving from specialized toolsets","year":"2023","author":"Yuan","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae075"},{"key":"ref51","article-title":"Building cooperative embodied agents modularly with large language models","author":"Zhang","year":"2024","journal-title":"ICLR"},{"key":"ref52","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","author":"Shen","year":"2024","journal-title":"NeuRIPS"},{"key":"ref53","article-title":"Learning to compose visual relations","author":"Liu","year":"2021","journal-title":"NeuRIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01088"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW58026.2022.00121"},{"article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","year":"2024","author":"Wang","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247340"},{"article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","year":"2023","author":"Yang","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801661"},{"article-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action","year":"2023","author":"Yang","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01417"},{"article-title":"Nbmod: Find it and grasp it in noisy background","year":"2023","author":"Cao","key":"ref63"},{"key":"ref64","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3019967"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref67","article-title":"Scaling open-vocabulary object detection","author":"Minderer","year":"2024","journal-title":"NeuRIPS"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802256"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11245817"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128811"},{"article-title":"Maniskill3: Gpu parallelized robotics simulation and rendering for generalizable embodied ai","year":"2024","author":"Tao","key":"ref71"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2023.102970"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246582.pdf?arnumber=11246582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:46Z","timestamp":1766061406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246582","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}