https://cmu-agent-workshop.github.io/_next/static/chunks/pages/Pre…/posters-26d939b3f3479e7f.js

1(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[82],{3794:function(e,n,i){(window.__NEXT_P=window.__NEXT_P||[]).push(["/Previous_Schedule_2024/posters",function(){return i(203)}])},203:function(e,n,i){"use strict";i.r(n),i.d(n,{__toc:function(){return l}});var r=i(5893),a=i(2673),s=i(1218),o=i(1255);i(9488);var t=i(2643);let l=[{depth:2,value:"Call for Posters",id:"call-for-posters"},{depth:3,value:"Important Dates",id:"important-dates"},{depth:3,value:"Submission Format",id:"submission-format"},{depth:3,value:"Topics of Interest",id:"topics-of-interest"},{depth:3,value:"Organizing Committee",id:"organizing-committee"}];function h(e){let n=Object.assign({h1:"h1",ul:"ul",li:"li",a:"a",br:"br",p:"p",strong:"strong",h2:"h2",h3:"h3",em:"em",ol:"ol"},(0,t.a)(),e.components);return(0,r.jsxs)(r.Fragment,{children:[(0,r.jsx)(n.h1,{children:"Posters"}),"\n",(0,r.jsxs)(n.ul,{children:["\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2307.13854",children:"WebArena: A Realistic Web Environment for Building Autonomous Agents"}),(0,r.jsx)(n.br,{}),"\n","Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, Graham Neubig"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2401.13649",children:"VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks"}),(0,r.jsx)(n.br,{}),"\n","Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, Po-Yu Huang, Graham Neubig, Shuyan Zhou, Ruslan Salakhutdinov, Daniel Fried"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/pdf/2401.12869.pdf",children:"TROVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks"}),(0,r.jsx)(n.br,{}),"\n","Zhiruo Wang, Daniel Fried, Graham Neubig"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2403.15452",children:"What Are Tools Anyway? A Survey from the Language Model Perspective"}),(0,r.jsx)(n.br,{}),"\n","Zhiruo Wang, Zhoujun Cheng, Hao Zhu, Daniel Fried, Graham Neubig"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2310.11667",children:"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents"}),(0,r.jsx)(n.br,{}),"\n","Xuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang, Haofei Yu, Zhengyang Qi, Louis-Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig, Maarten Sap"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2404.06474",children:"Autonomous Evaluation and Refinement of Digital Agents"}),(0,r.jsx)(n.br,{}),"\n","Jiayi Pan, Yichi Zhang, Nicholas Tomlin, Yifei Zhou, Sergey Levine, Alane Suhr"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2402.19446",children:"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"}),(0,r.jsx)(n.br,{}),"\n","Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2404.00566",children:"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks"}),(0,r.jsx)(n.br,{}),"\n","Yiqing Xie, Alex Xie, Divyanshu Sheth, Pengfei Liu, Daniel Fried, Carolyn Rose"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1tdYG84X6z_ctKXt9yNQqQSjkOdZ6HXHm",children:"VHABench: Benchmarking Underspecified User Intents for Tool Augmented LLMs"}),(0,r.jsx)(n.br,{}),"\n","Eduardo Trevino, Rohit Malhotra, Hugo Contant"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=16sZk_yWDaLLYUj62AAxyOlF9XWHG91IF",children:"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews"}),(0,r.jsx)(n.br,{}),"\n","Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, Yanghua Xiao"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1C9cPjV875I--fxlWvLd8XfiIP8S9O1WV",children:"Can large language models explore in-context?"}),(0,r.jsx)(n.br,{}

1),"\n","Akshay Krishnamurthy, Keegan Harris, Dylan J Foster, Cyril Zhang, Aleksandrs Slivkins"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1pwx0-GeWc3-JkpmjmJQ_GWGxCO0tlyAn",children:"Building a Financial Chatbot Using Langroid's Multi-Agent Framework"}),(0,r.jsx)(n.br,{}),"\n","Karthik Talluri, Vu Nguyen, Saanika Shahi, Antony Liao"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1tQVVvGVCPxseZ7nHGnOiRp_hUIJOIuV2",children:"What Is Missing in Multilingual Visual Reasoning and How to Fix It"}),(0,r.jsx)(n.br,{}),"\n","Yueqi Song, Simran Khanuja, Graham Neubig"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=18Igl5o-HW1YYuKNQpTcED2C2QBCuSt-y",children:"LLM-Accelerated Tool Generation for Code Analysis"}),(0,r.jsx)(n.br,{}),"\n","Shen Zhang, Ryan Karl, Yash Hindka"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1IOQccWyO619uN3ztfXqNavNHTwHdOHQd",children:"Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models"}),(0,r.jsx)(n.br,{}),"\n","Gabriel Sarch, Yue Wu, Sahil Somani, Raghav Kapoor, Michael Tarr, Katerina Fragkiadaki"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1siG5_rS3XZN4naRTBDbPh2XcN_ax9hb4",children:"LLM-SR: Scientific Equation Discovery via Programming with Large Language Models"}),(0,r.jsx)(n.br,{}),"\n","Parshin Shojaee, Kazem Meidani, Shashank Gupta, Amir Barati Farimani, Chandan K. Reddy"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1Qk3qLlRr2KUrko5iIbacQJlCZv-mghYE",children:"How well do LLM Web Agents work for non-English Language?"}),(0,r.jsx)(n.br,{}),"\n","Abir Muhtasim, Arnab Bhattacharjee, Abhik Bhattacharjee, Faria Huq and Rifat Shahriyar"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1Hao_9xbFeCMeRLn4WR3t732WPY0YMW37",children:"Large Language Models for Collective Problem-Solving: Insights into Group Consensus Decision-Making"}),(0,r.jsx)(n.br,{}),"\n","Yinuo Du, Prashanth Rajivan, Cleotilde Gonzalez"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1SvH9mEGmiBuI0M0bAxhdCohgJ7-3qQnG",children:"Influence Maximization in Dynamical Social Networks via Reinforcement Learning with LLM-simulated User Behaviors and Graph Embeddings"}),(0,r.jsx)(n.br,{}),"\n","Yurun Tian"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1P7w02nIil8xuGSDAWNZOrFWWaNgXqPMF",children:"MemAgent: A cache-inspired framework for aligning LLM Web Agent with User Goal"}),(0,r.jsx)(n.br,{}),"\n","Faria Huq, Nazmus Sakib, Protoy Barai, Sifat Ishmam Parisa, Abhik Bhattacharjee, Anindya Iqbal"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://arxiv.org/abs/2404.11023",children:"Advancing Social Intelligence in AI Agents:  Technical Challenges and Open Questions"}),(0,r.jsx)(n.br,{}),"\n","Leena Mathur, Paul Pu Liang, Louis-Philippe Morency"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/open?id=1pbhjwsWSyR0ygjwrOchbsYLxkDd_Xd1P",children:"The Collaborative Caring Simulation Framework: Using LLM agents to simulate care-teams for prototyping and evaluating collective intelligence interventions"}),(0,r.jsx)(n.br,{}),"\n","Andrew Kuznetsov, Ping-Ya Chao, Christopher Dishop, Allen Brown, and Anita Woolley"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/file/d/1DIWxolQIQa9Gk_-Q0qR8bsg5LzR8DBKN/view?usp=sharing",children:"WebBug: Evaluating MultiModal Agents in Real-World Web Quality Analysis Testing"}),(0,r.jsx)(n.br,{}),"\n","Sneha Sivakumar, Anushka Nijhawan Arman Cohan"]}),"\n",(0,r.jsxs)(n.li,{children:[(0,r.jsx)(n.a,{href:"https://drive.google.com/file/d/1Jq6IXQWoSDkDwIrgCtebHV_GlItrFMIt/view?usp=sharing",children:"AutoTester: An LMM Web-Agent for Automated Web Quality Assurance Testing"}),(0,r.jsx)(n.br,{}),"\n","Anushka Nijhawan, Sneha Sivakumar, Arman Cohan"]}),"\n",(0,r.jsx)(n.li,{children:"... and more to come!"}),"\n"]}),"\n",(0,r.jsx)(n.p,{children:(0,r.jsxs)(n.strong,{children:["Submit your poster at ",(0,r.jsx)(n.a,{href:"https://forms.gle/sWgMhXrjX4cnoiGA8",children:"https://forms.gle/sWgMhXrjX4cnoiGA8"})," and present in person!"]})}),"\n",(0,r.jsx)(n.h2,{id:"call-for-posters",children:"Call for Posters"}),"\n",(0,r.jsx)(n.p,{children:"We are excited to announce our LLM Agent Workshop on May 2-3."}),"\n",(0,r.jsx)(n.p,{children:"Our workshop is a CMU-wide event for students to show their recent and/or ongoing research and projects to the community. Any work related to LLM situating in, perceiving, and acting upon an external environment is welcomed.\r\nSubmissions from students will be presented at the poster session in our workshop. This would be a great opportunity to publicize your projects and gain valuable feedback from the community!"}),"\n",(0,r.jsx)(n.h3,{id:"important-dates",children:"Important Dates"}),"\n",(0,r.jsxs)(n.ul,{children:["\n",(0,r.jsxs)(n.li,{children:["Submission Deadline: ",(0,r.jsx)(n.em,{children:"Apr 30, 2024"})]}),"\n",(0,r.jsxs)(n.li,{children:["Presentation Time/Date: ",(0,r.jsx)(n.em,{children:"May 2nd, 2024, 3:00-5:30 pm"}),". In-person at ",(0,r.jsx)(n.a,{href:"https://www.cmu.edu/cohon-university-center/images/floor-plans/CUC_2.pdf",children:"Cohon University Center, Rangos Ballroom 1"})]}),"\n"]}),"\n",(0,r.jsx)(n.h3,{id:"submission-format",children:"Submission Format"}),"\n",(0,r.jsx)(n.p,{children:"Please prepare materials in the following two formats:"}),"\n",(0,r.jsxs)(n.ol,{children:["\n",(0,r.jsx)(n.li,{children:"A poster in the .pdf format, with any reasonable size, landscape or portrait (you can print out your slides if you are feeling lazy :))."}),"\n",(0,r.jsx)(n.li,{children:"A short abstract of your work"}),"\n"]}),"\n",(0,r.jsx)(n.p,{children:"You’re welcome to submit projects at any stage, including side projects, submissions to other conferences, course projects, and any ongoing projects."}),"\n",(0,r.jsxs)(n.p,{children:["Please submit your project via this google form: ",(0,r.jsx)(n.a,{href:"https://forms.gle/sWgMhXrjX4cnoiGA8",children:"https://forms.gle/sWgMhXrjX4cnoiGA8"})," , and bring your poster. It can be printed via ",(0,r.jsx)(n.a,{href:"https://www.cmu.edu/tartanink/",children:"Tartan Ink"})," or ",(0,r.jsx)(n.a,{href:"https://computing.cs.cmu.edu/desktop/printing-posters",children:"SCS Poster Printing"})," if you are part of SCS community. If for some reason you are unable to print the poster, please email us notifying this!"]}),"\n",(0,r.jsx)(n.h3,{id:"topics-of-interest",children:"Topics of Interest"}),"\n",(0,r.jsx)(n.p,{children:"Topics include, but are not limited to:"}),"\n",(0,r.jsxs)(n.ul,{children:["\n",(0,r.jsx)(n.li,{children:"LLM agents, environments, and tool use"}),"\n",(0,r.jsx)(n.li,{children:"LLM reasoning"}),"\n",(0,r.jsx)(n.li,{children:"LLM agents learning: expert supervision, reinfor

1cement learning, synthetic data augmentation, etc."}),"\n",(0,r.jsx)(n.li,{children:"Open source software of LLM tool use and agents: browser plugin, AI assistant, toolbox, environment, framework, etc."}),"\n",(0,r.jsx)(n.li,{children:"Multi-agent interaction: human agent and model-based agent"}),"\n",(0,r.jsx)(n.li,{children:"Specific interesting tasks and domains: e.g., knowledge exploration, software engineering, scientific discovery, social intelligence"}),"\n",(0,r.jsx)(n.li,{children:"Safety of LLM agents"}),"\n",(0,r.jsx)(n.li,{children:"Ethics and societal impact of LLM agents: job market, economic impact, accessibility, etc."}),"\n"]}),"\n",(0,r.jsx)(n.h3,{id:"organizing-committee",children:"Organizing Committee"}),"\n",(0,r.jsxs)(n.ul,{children:["\n",(0,r.jsxs)(n.li,{children:["Frank Xu: ",(0,r.jsx)(n.a,{href:"mailto:[email protected]",children:"[email protected]"})]}),"\n",(0,r.jsxs)(n.li,{children:["Zora Wang: ",(0,r.jsx)(n.a,{href:"mailto:[email protected]",children:"[email protected]"})]}),"\n",(0,r.jsxs)(n.li,{children:["Shuyan Zhou: ",(0,r.jsx)(n.a,{href:"mailto:[email protected]",children:"[email protected]"})]}),"\n"]}),"\n",(0,r.jsx)(n.p,{children:"Feel free to contact the LLM Agent Workshop organizers if you have any questions!"})]})}let c={MDXContent:function(){let e=arguments.length>0&&void 0!==arguments[0]?arguments[0]:{},{wrapper:n}=Object.assign({},(0,t.a)(),e.components);return n?(0,r.jsx)(n,{...e,children:(0,r.jsx)(h,{...e})}):h(e)},pageOpts:{filePath:"pages/Previous_Schedule_2024/posters.mdx",route:"/Previous_Schedule_2024/posters",timestamp:1746144668e3,pageMap:[{kind:"Folder",name:"Previous_Schedule_2024",route:"/Previous_Schedule_2024",children:[{kind:"Meta",data:{index:"Homepage",social_agent:"Social Agent Seminar",schedule:"Schedule",speakers:"Speakers",posters:"Poster Session",tutorials:"Tutorials",hackathon:"Hackathon"}},{kind:"MdxPage",name:"hackathon",route:"/Previous_Schedule_2024/hackathon"},{kind:"MdxPage",name:"index",route:"/Previous_Schedule_2024"},{kind:"MdxPage",name:"posters",route:"/Previous_Schedule_2024/posters"},{kind:"MdxPage",name:"schedule",route:"/Previous_Schedule_2024/schedule"},{kind:"MdxPage",name:"social_agent",route:"/Previous_Schedule_2024/social_agent"},{kind:"MdxPage",name:"speakers",route:"/Previous_Schedule_2024/speakers"},{kind:"MdxPage",name:"tutorials",route:"/Previous_Schedule_2024/tutorials"}]},{kind:"Meta",data:{index:"Homepage",schedule:"Schedule",speakers:"Speakers",posters:"Poster Session",organizers:"Workshop Organizer Committee",Previous_Schedule_2024:"Previous Schedule 2024"}},{kind:"MdxPage",name:"index",route:"/"},{kind:"MdxPage",name:"organizers",route:"/organizers"},{kind:"MdxPage",name:"posters",route:"/posters"},{kind:"MdxPage",name:"schedule",route:"/schedule"},{kind:"MdxPage",name:"speakers",route:"/speakers"}],flexsearch:{codeblocks:!0},title:"Posters",headings:l},pageNextRoute:"/Previous_Schedule_2024/posters",nextraLayout:s.ZP,themeConfig:o.Z};n.default=(0,a.j)(c)},1255:function(e,n,i){"use strict";var r=i(5893);n.Z={logo:(0,r.jsxs)(r.Fragment,{children:[(0,r.jsx)("img",{width:"36",height:"36",src:"/logo.svg",alt:"Agent Workshop @ CMU"}),(0,r.jsx)("span",{style:{marginLeft:".4em",fontWeight:800},children:"Agent Workshop @ Carnegie Mellon University"})]}),project:{link:"https://cmu-agent-workshop.github.io/"},search:{placeholder:"Search contents"},feedback:{content:null},edit:{content:null},footer:{text:(0,r.jsxs)("span",{children:["MIT ",new Date().getFullYear()," \xa9"," ","CMU Agent Workshop Organizers ."]})},head:(0,r.jsxs)(r.Fragment,{children:[(0,r.jsx)("link",{rel:"icon",href:"/logo.svg",type:"image/svg+xml"}),(0,r.jsx)("link",{rel:"icon",href:"/icon.ico",type:"image/ico"})]}),useNextSeoProps:()=>({titleTemplate:"%s – LLM Agents workshop at CMU April 10-11",description:"We are hosting LLM Agents workshop at Carnegie Mellon University, Pittsburgh, PA, USA on April 10-11.",openGraph:{type:"website",images:[{url:"https://cmu-agent-workshop.github.io/cover.jpg"}],locale:"en_US",url:"https://cmu-agent-workshop.github.io/",siteName:"LLM Agents workshop at CMU April 10-11",description:"We are hosting LLM Agents workshop at Carnegie Mellon University, Pittsburgh, PA, USA on April 10-11."},twitter:{cardType:"summary_large_image",image:"https://cmu-agent-workshop.github.io/cover.jpg"}})}},5789:function(){}},function(e){e.O(0,[694,888,774,179],function(){return e(e.s=3794)}),_N_E=e.O()}]);