[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86425-en":3,"doc-seo-86425-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86425,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","FARS: A Fully Automated Research System Deployed at Scale","FARS (Fully Automated Research System) is an end-to-end AI-for-AI research system built to run continuously at scale without human intervention during execution. It autonomously drives projects from ideation and planning through experimentation and manuscript writing, coordinating stage-specific agents via a shared workspace that records proposals, code, logs, results, and drafts. In its first public deployment, FARS generated 166 complete research papers across 67 fine-grained AI/ML topics and preserved intermediate artifacts as an auditable corpus. Structured reviews of 140 papers assess quality, integrity, and LLM-use disclosure, revealing strengths and recurring failure modes.","arXiv :2606 .3 165 1v2 [ cs .AI] 13 Jul 2026  \nFARS: A FULLY AUTOMATED RESEARCH SYSTEM DEPLOYED AT SCALE  \nAuthors  \nQiong Tang†, Tianxiang Sun†, Xiangkun Hu†, Xiangyang Liu†, Yiran Chen†, Yunfan Shao† Analemma  \n{qtang,txsun,xkhu,xyliu,yrchen,[yfshao](yfshao}@analemma.ai)[}](yfshao}@analemma.ai)[@analemma.ai](yfshao}@analemma.ai)  \nReviewers‡  \nBobo Li 1 , Changze Lv2 , Cheng Xu3 , Chengsong Huang4 , Chunyang Li5 , Dizhan Xue6 , Hao Bai7 , Haodong Duan8 , Hengquan Guo9 , Hongyang He 10 , Hongyi Chen 11 , Hui Shen 12 , Jiahao Yuan 13 , Jiankai Sun 14 , Jikang Cheng 15 , Jinfeng Xu 16 , Jingqi Tong2,17 , Jingye Chen5 , Jinxiu Liu 18 , Jixuan Leng 11 , Junchi Yu 19 , Kaixun Jiang2 , Kun Xiang20 , Kunpeng Yao21 , Lang Feng22 , Liangqi Yuan23 , Longsen Gao24 , Meng Li25 , Qi Jia26 , Qiushi Sun 16 , Shengyuan Ding2 , Shizhan Gong27 , Siru Zhong28 , Terry Jingchen Zhang29 , Tianle Gu30 , Tianyi Liang 17,31 , Weijie Liu 15 , Weikai Yang28 , Weizhi Fei30 , Xiangkun Hu32 , Xiangyang Liu32 , Xin Wang33 , Xinpeng Liu34 , Xuanwen Ding2 , Yihong Tang35,36 , Yuanli Wang37 , Yukun Jiang38 , Yuming Yang2 , Zhengbao He34 , Zhikai Chen39 , Zhikun Xu40 , Zhuang Li41 , Zihao Huang8 , Anonymous, Anonymous  \n1National University of Singapore, 2Fudan University, 3University College Dublin, 4Washington University in St. Louis, 5The Hong Kong University of Science and Technology, 6Institute of Automation, Chinese Academy of Sciences, 7University of Illinois at Urbana-Champaign, 8ByteDance, 9 ShanghaiTech University, 10University of Warwick, 11Carnegie Mellon University, 12University of Michigan, Ann Arbor, 13East China Normal University, 14 Stanford University, 15Tencent, 16The University of Hong Kong, 17 Shanghai Innovation Institute, 18Nex-AGI Team, 19University of Oxford, 20 Sun Yat-sen University, 21University of Leeds, 22Nanyang Technological University, 23Purdue University, 24University of New Mexico, 25Nanjing University, 26 Shanghai Artificial Intelligence Laboratory, 27The Chinese University of Hong Kong, 28The Hong Kong University of Science and Technology (Guangzhou), 29Vector Institute, 30Tsinghua University, 31 OpenMOSS, 32Analemma, 33The Ohio State University, 34 Shanghai Jiao Tong University, 35McGill University, 36 ServiceNow AIResearch, 37Boston University, 38CISPA-Helmholtz-Zentrum f¨ur Informationssicherheit gGmbH, 39Michigan State University, 40Arizona State University, 41RMIT University  \n†Equal contribution; human authors listed in alphabetical order by first name.‡Named reviewers are listed alphabetically.  \nABSTRACT  \nRecent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selected examples, human-framed topics, or a few predefined research tasks. We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system designed to operate across research topics at scale. FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing, using stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts. In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics while preserving intermediate artifacts as an auditable corpus rather than a curated set of successes.  \nWe evaluate this corpus with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure. The reviews indicate that FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment, while also exposing recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.  \n1 INTRODUCTION  \nRecent progress in autonomous research systems suggests that language-model agents can now perform substantial portions","cbCaioRAtvacTArB","https://ap.wps.com/l/cbCaioRAtvacTArB","pdf",3720742,3,1,20,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What is the main goal of FARS?\",\"answer\":\"FARS aims to efficiently and reliably expand the frontier of knowledge by automating the complete research workflow at scale without human intervention during execution.\"},{\"question\":\"How does FARS manage its automated research workflow?\",\"answer\":\"FARS uses stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts as auditable intermediate artifacts.\"},{\"question\":\"What evidence was collected from the first public deployment of FARS?\",\"answer\":\"The deployment produced 166 complete research papers spanning 67 fine-grained AI/ML topics, and the resulting corpus was evaluated using structured reviews from volunteer reviewers covering 140 papers, including integrity checks and LLM-use disclosure.\"}]",1784211673,50,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"fars-a-fully-automated-research-system-deployed-at-scale","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/fars-a-fully-automated-research-system-deployed-at-scale/86425/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of FARS?","Question",{"text":75,"@type":76},"FARS aims to efficiently and reliably expand the frontier of knowledge by automating the complete research workflow at scale without human intervention during execution.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does FARS manage its automated research workflow?",{"text":80,"@type":76},"FARS uses stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts as auditable intermediate artifacts.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence was collected from the first public deployment of FARS?",{"text":84,"@type":76},"The deployment produced 166 complete research papers spanning 67 fine-grained AI/ML topics, and the resulting corpus was evaluated using structured reviews from volunteer reviewers covering 140 papers, including integrity checks and LLM-use disclosure.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":29,"slug":113},6,"Technology","technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":22,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":22,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]