{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T02:10:30Z","timestamp":1732673430896,"version":"3.28.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"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":[[2024,8,28]]},"DOI":"10.1109\/icac61394.2024.10718742","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T17:41:15Z","timestamp":1729705275000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["AUTONODE: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automation"],"prefix":"10.1109","author":[{"given":"Arkajit","family":"Datta","sequence":"first","affiliation":[{"name":"SuperAGI Research,Palo Alto,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tushar","family":"Verma","sequence":"additional","affiliation":[{"name":"SuperAGI Research,Palo Alto,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajat","family":"Chawla","sequence":"additional","affiliation":[{"name":"SuperAGI Research,Palo Alto,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mukunda N.","family":"S","sequence":"additional","affiliation":[{"name":"SuperAGI Research,Palo Alto,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ishaan","family":"Bhola","sequence":"additional","affiliation":[{"name":"SuperAGI Research,Palo Alto,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref3","first-page":"1","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","volume":"9","author":"Yang","year":"2023"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref4"},{"article-title":"Appagent: Multimodal agents as smartphone users","year":"2023","author":"Yang","key":"ref5"},{"article-title":"Guiding instruction-based image editing via multimodal large language models","year":"2023","author":"Fu","key":"ref6"},{"article-title":"Os-copilot: Towards generalist computer agents with self-improvement","year":"2024","author":"Wu","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/machines11070677"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7074-2_3"},{"article-title":"Knowledge-guided exploration in deep reinforcement learning","year":"2022","author":"Mazumder","key":"ref12"},{"article-title":"Learning human actions on computer applications","volume-title":"rabbit research team","year":"2023","key":"ref13"},{"key":"ref14","article-title":"Mind2web: Towards a generalist agent for the web","volume":"36","author":"Deng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Reinforcement learning on web interfaces using workflow-guided exploration","year":"2018","author":"Liu","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236882"},{"key":"ref17","article-title":"On the importance of exploration for generalization in reinforcement learning","volume":"36","author":"Jiang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Guided exploration in reinforcement learning via monte carlo critic optimization","year":"2022","author":"Kuznetsov","key":"ref18"},{"article-title":"Veagle: Advancements in multimodal representation learning","year":"2024","author":"Chawla","key":"ref19"},{"article-title":"Mm1: Methods, analysis & insights from multimodal llm pre-training","year":"2024","author":"McKinzie","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01354"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/0201010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29875"},{"article-title":"Graph-toolformer: To empower llms with graph reasoning ability via prompt augmented by chatgpt","year":"2023","author":"Zhang","key":"ref24"},{"article-title":"K-link: Knowledge-link graph from llms for enhanced representation learning in multivariate time-series data","year":"2024","author":"Wang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.738"},{"article-title":"Llm-brain: Ai-driven fast generation of robot behaviour tree based on large language model","year":"2023","author":"Lykov","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00630-8"},{"key":"ref29","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"International Conference on machine learning","author":"Guu"},{"article-title":"React: Synergizing reasoning and acting in language models","year":"2022","author":"Yao","key":"ref30"},{"article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","year":"2021","author":"Liu","key":"ref31"}],"event":{"name":"2024 29th International Conference on Automation and Computing (ICAC)","start":{"date-parts":[[2024,8,28]]},"location":"Sunderland, United Kingdom","end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 29th International Conference on Automation and Computing (ICAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10718699\/10718729\/10718742.pdf?arnumber=10718742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:53:30Z","timestamp":1732672410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10718742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icac61394.2024.10718742","relation":{},"subject":[],"published":{"date-parts":[[2024,8,28]]}}}