{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T05:34:14Z","timestamp":1775712854779,"version":"3.50.1"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB4505800"],"award-info":[{"award-number":["2024YFB4505800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025404"],"award-info":[{"award-number":["62025404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["Z241100004224015"],"award-info":[{"award-number":["Z241100004224015"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128047","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["KARMA: Augmenting Embodied AI Agents with Long-and-Short Term Memory Systems"],"prefix":"10.1109","author":[{"given":"Zixuan","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Science (CASIA)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junzhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai","family":"Hou","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Liang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinhe","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Gan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Lota-bench: Benchmarking language-oriented task planners for embodied agents","author":"Choi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Helper-x: A unified instructable embodied agent to tackle four interactive vision-language domains with memory-augmented language models","author":"Sarch","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Llm-state: Expandable state representation for long-horizon task planning in the open world","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3387941"},{"key":"ref5","first-page":"23","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","volume-title":"Proceedings of The 7th Conference on Robot Learning, ser. Proceedings of Machine Learning Research","volume":"229","author":"Rana","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref7","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.226"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.316"},{"key":"ref12","article-title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Shridhar","year":"2021"},{"key":"ref13","article-title":"AI2-THOR: An Interactive 3D Environment for Visual AI","author":"Kolve","year":"2017","journal-title":"arXiv"},{"key":"ref14","article-title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","volume-title":"International Conference on Machine Learning","author":"Huang","year":"2022"},{"key":"ref15","article-title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Language Models are Few-shot Learners","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.90"},{"key":"ref18","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref21","article-title":"Embodied task planning with large language models","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.814"},{"key":"ref23","article-title":"Chatharuhi: Reviving anime character in reality via large language model","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.878"},{"key":"ref25","article-title":"Characterglm: Customizing chinese conversational ai characters with large language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-demo.10"},{"key":"ref27","article-title":"Lyfe agents: Generative agents for low-cost real-time social interactions","author":"Kaiya","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4607026"},{"key":"ref30","article-title":"Metaagents: Simulating interactions of human behaviors for llm-based task-oriented coordination via collaborative generative agents","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref31","article-title":"War and peace (waragent): Large language model-based multi-agent simulation of world wars","author":"Hua","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29946"},{"key":"ref33","article-title":"Ret-llm: Towards a general read-write memory for large language models","author":"Modarressi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Memochat: Tuning llms to use memos for consistent long-range opendomain conversation","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Memgpt: Towards llms as operating systems","author":"Packer","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.277"},{"key":"ref37","article-title":"Autogen: Enabling next-gen llm applications via multi-agent conversation framework","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Chatdb: Augmenting llms with databases as their symbolic memory","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Think-in-memory: Recalling and post-thinking enable llms with longterm memory","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Unleashing infinite-length input capacity for large-scale language models with self-controlled memory system","author":"Liang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Jarvis-1: Open-world multi-task agents with memory-augmented multimodal language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Larp: Language-agent role play for open-world games","author":"Yan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657353"},{"key":"ref46","article-title":"Gamegpt: Multiagent collaborative framework for game development","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.737"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.271"},{"key":"ref50","article-title":"c. when large language model based agent meets user behavior analysis: A novel user simulation paradigm","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645537"},{"key":"ref52","article-title":"Huatuo: Tuning llama model with chinese medical knowledge","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Investlm: A large language model for investment using financial domain instruction tuning","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Chemdfm: Dialogue foundation model for chemistry","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","article-title":"Retrieval-augmented generation for ai-generated content: A survey","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref56","article-title":"From local to global: A graph rag approach to queryfocused summarization","author":"Edge","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref57","article-title":"Rap: Retrieval-augmented planning with contextual memory for multimodal 1 lm agents","author":"Kagaya","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Building cooperative embodied agents modularly with large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01004"},{"key":"ref60","article-title":"Mc-gpt: Empowering vision-andlanguage navigation with memory map and reasoning chains","author":"Zhan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Mobility vla: Multimodal instruction navigation with long-context vlms and topological graphs","author":"Chiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211056674"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00576"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10802322"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2014.34"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2889329"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.226"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref69","article-title":"Dadu-e: Rethinking the role of large language model in robotic computing pipeline","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128047.pdf?arnumber=11128047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:11:42Z","timestamp":1756879902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128047","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}