{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:09:54Z","timestamp":1781672994189,"version":"3.54.5"},"reference-count":34,"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\/iros60139.2025.11247340","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"20386-20393","source":"Crossref","is-referenced-by-count":6,"title":["MALMM: Multi-Agent Large Language Models for Zero-Shot Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Harsh","family":"Singh","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rocktim Jyoti","family":"Das","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingfei","family":"Han","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Preslav","family":"Nakov","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Rvt: Robotic view transformer for 3d object manipulation","author":"Goyal","year":"2023"},{"key":"ref2","first-page":"3949","article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","volume-title":"conference on Robot Learning","author":"Gervet"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1090\/bull\/1828"},{"key":"ref5","article-title":"Chain of thought prompting elicits reasoning in large language models","author":"Wei"},{"key":"ref6","doi-asserted-by":"crossref","article-title":"Evaluating very long-term conversational memory of llm agents","author":"Maharana","DOI":"10.18653\/v1\/2024.acl-long.747"},{"key":"ref7","article-title":"Learning to interpret natural language commands through human-robot dialog","volume-title":"International Joint Conference on Artificial Intelligence","author":"Thomason"},{"key":"ref8","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"Jang","year":"2022"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-28572-1_3","article-title":"Grounding verbs of motion in natural language commands to robots","volume-title":"International Symposium on Experimental Robotics","author":"Kollar"},{"key":"ref10","article-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback","author":"Wang","year":"2024"},{"key":"ref11","first-page":"6728","article-title":"Language models as zero-shot trajectory generators","volume-title":"IEEE Robotics and Automation Letters","volume":"9","author":"Kwon","year":"2023"},{"key":"ref12","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"conference on Robot Learning","author":"Huang"},{"key":"ref13","article-title":"Llm+ p: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023"},{"key":"ref14","article-title":"Reflect: Summarizing robot experiences for failure explanation and correction","author":"Liu","year":"2023"},{"key":"ref15","first-page":"9493","article-title":"Code as policies: Language model programs for embodied control","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","author":"Liang"},{"key":"ref16","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref17","article-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023"},{"key":"ref18","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023"},{"key":"ref19","first-page":"286","article-title":"Roco: Dialectic multi-robot collaboration with large language models","volume-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","author":"Mandi"},{"key":"ref20","article-title":"Collaborating with language models for embodied reasoning","author":"Dasgupta","year":"2023"},{"key":"ref21","first-page":"10 608","article-title":"Visual language maps for robot navigation","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","author":"Huang"},{"key":"ref22","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","author":"Huang","year":"2022"},{"key":"ref23","first-page":"3019","article-title":"Rlbench: The robot learning benchmark & learning environment","volume-title":"IEEE Robotics and Automation Letters","volume":"5","author":"James","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref25","article-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","author":"Chen","year":"2022"},{"key":"ref26","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref27","article-title":"Language segment-anything","author":"Medeiros","year":"2024"},{"key":"ref28","article-title":"M2t2: Multi-task masked transformer for object-centric pick and place","volume-title":"conference on Robot Learning","author":"Yuan"},{"key":"ref29","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref30","article-title":"Autogen: Enabling next-gen llm applications via multi-agent conversation","author":"Wu","year":"2023"},{"key":"ref31","article-title":"MALMM project webpage"},{"key":"ref32","first-page":"101532","article-title":"Taming the panda with python: A powerful duo for seamless robotics programming and integration","volume-title":"SoftwareX","volume":"24","author":"Elsner","year":"2023"},{"key":"ref33","article-title":"Llms will always hallucinate, and we need to live with this","author":"Banerjee","year":"2024"},{"key":"ref34","article-title":"Manipulate-anything: Automating real-world robots using vision-language models","author":"Duan","year":"2024"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11247340.pdf?arnumber=11247340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:50Z","timestamp":1766061650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247340","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}