{"672268":{"#nid":"672268","#data":{"type":"event","title":"CSE Faculty Candidate Seminar - Shuyan Zhou","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EName: \u003C\/strong\u003EShuyan Zhou, Ph.D. student at Carnegie Mellon University\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate:\u0026nbsp;\u003C\/strong\u003EThursday, February 1, 2024 at 11:00 am\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation:\u003C\/strong\u003E\u0026nbsp;Coda Building, First Floor, Room 114 (\u003Ca href=\u0022https:\/\/www.google.com\/maps\/place\/Coda\/@33.7752651,-84.3876426,15z\/data=!4m6!3m5!1s0x88f5046677950223:0x7fd1ad077b382c98!8m2!3d33.7752651!4d-84.3876426!16s%2Fg%2F11c6lvs7sl?entry=ttu\u0022\u003EGoogle Maps link\u003C\/a\u003E)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELink:\u0026nbsp;\u003C\/strong\u003EThe recording of this in-person seminar will be uploaded to\u0026nbsp;\u003Ca href=\u0022https:\/\/mediaspace.gatech.edu\/channel\/School%2Bof%2BComputational%2BScience%2Band%2BEngineering\/259332602\u0022 target=\u0022_blank\u0022\u003ECSE\u0027s MediaSpace\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETitle:\u0026nbsp;\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003ESolving Real-World Tasks with AI Agents\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u0026nbsp;\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003EFor years, my dream has been to create autonomous AI agents capable of carrying out tedious procedural tasks (e.g., arranging conference travel), allowing me to focus on more creative and exciting tasks. Modern AI models, especially large language models (LLMs) like ChatGPT, have suddenly brought us much closer to achieving such AI agents. But, has my dream already come true? In this talk, I will answer this question by delving into my systematic evaluation of AI agents in realistic tasks. The evaluation uncovers many critical limitations of AI agents, such as accurate grounding, long-term planning, and tool use. It suggests that LLMs are crucial yet early steps towards AI autonomy. To address these challenges,\u0026nbsp; I will introduce my research of a more suitable \u201clanguage\u201d for AIs, which overcomes the inherent limitations of using natural language for task solving. Finally, I will discuss my work on teaching AI agents to learn new tools by reading the tool documentation rather than direct demonstrations.\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EBio:\u0026nbsp;\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003EShuyan Zhou is a final-year Ph.D. student at the Language Technologies Institute at CMU, advised by Graham Neubig. Her research in NLP and AI focuses on creating AI agents for real-world tasks, such as using computers and generating code. Her work has been recognized at top natural language processing and machine learning conferences and journals such as ICLR, ICML, ACL, EMNLP, and TACL. You can find more about her at https:\/\/shuyanzhou.com\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003EName: \u003C\/strong\u003EShuyan Zhou, Ph.D. student at Carnegie Mellon University\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate:\u0026nbsp;\u003C\/strong\u003EThursday, February 1, 2024 at 11:00 am\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation:\u003C\/strong\u003E\u0026nbsp;Coda Building, First Floor, Room 114 (\u003Ca href=\u0022https:\/\/www.google.com\/maps\/place\/Coda\/@33.7752651,-84.3876426,15z\/data=!4m6!3m5!1s0x88f5046677950223:0x7fd1ad077b382c98!8m2!3d33.7752651!4d-84.3876426!16s%2Fg%2F11c6lvs7sl?entry=ttu\u0022\u003EGoogle Maps link\u003C\/a\u003E)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELink:\u0026nbsp;\u003C\/strong\u003EThe recording of this in-person seminar will be uploaded to\u0026nbsp;\u003Ca href=\u0022https:\/\/mediaspace.gatech.edu\/channel\/School%2Bof%2BComputational%2BScience%2Band%2BEngineering\/259332602\u0022 target=\u0022_blank\u0022\u003ECSE\u0027s MediaSpace\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETitle:\u0026nbsp;\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003ESolving Real-World Tasks with AI Agents\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"Seminar Title:\u00a0Solving Real-World Tasks with AI Agents"}],"uid":"36319","created_gmt":"2024-01-18 19:39:38","changed_gmt":"2024-01-22 15:38:38","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-02-01T11:00:00-05:00","event_time_end":"2024-02-01T12:00:00-05:00","event_time_end_last":"2024-02-01T12:00:00-05:00","gmt_time_start":"2024-02-01 16:00:00","gmt_time_end":"2024-02-01 17:00:00","gmt_time_end_last":"2024-02-01 17:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Coda, Room 114","extras":[],"hg_media":{"672828":{"id":"672828","type":"image","title":"shuyan_zhou_headshot hg.jpg","body":null,"created":"1705937699","gmt_created":"2024-01-22 15:34:59","changed":"1705937699","gmt_changed":"2024-01-22 15:34:59","alt":"Shuyan Zhou seminar headshot","file":{"fid":"256147","name":"shuyan_zhou_headshot hg.jpg","image_path":"\/sites\/default\/files\/2024\/01\/22\/shuyan_zhou_headshot%20hg.jpg","image_full_path":"http:\/\/tlwarc.hg.gatech.edu\/\/sites\/default\/files\/2024\/01\/22\/shuyan_zhou_headshot%20hg.jpg","mime":"image\/jpeg","size":96278,"path_740":"http:\/\/tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/01\/22\/shuyan_zhou_headshot%20hg.jpg?itok=uGVOcSwc"}}},"media_ids":["672828"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[],"keywords":[{"id":"166983","name":"School of Computational Science and Engineering"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EMary High\u003Cbr \/\u003E\r\nmhigh7@gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}