Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456 Paper page - The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios
https://github.com/KnowledgeXLab/EvoEnv\n","updatedAt":"2026-01-15T01:06:15.783Z","author":{"_id":"64673506b990713c503079bc","avatarUrl":"/avatars/17396c835f1eeae00ec2972b6a24a2dd.svg","fullname":"Fu","name":"fudaocheng","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":2,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8772719502449036},"editors":["fudaocheng"],"editorAvatarUrls":["/avatars/17396c835f1eeae00ec2972b6a24a2dd.svg"],"reactions":[],"isReport":false}},{"id":"696844f2fae0009234f64483","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2026-01-15T01:37:54.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction](https://huggingface.co/papers/2601.06966) (2026)\n* [IDRBench: Interactive Deep Research Benchmark](https://huggingface.co/papers/2601.06676) (2026)\n* [Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios](https://huggingface.co/papers/2601.01857) (2026)\n* [OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent](https://huggingface.co/papers/2601.07779) (2026)\n* [ToolGym: an Open-world Tool-using Environment for Scalable Agent Testing and Data Curation](https://huggingface.co/papers/2601.06328) (2026)\n* [NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents](https://huggingface.co/papers/2512.12730) (2025)\n* [From Failure to Mastery: Generating Hard Samples for Tool-use Agents](https://huggingface.co/papers/2601.01498) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\n
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
\n
If you want recommendations for any Paper on Hugging Face checkout this Space
\n
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
\n","updatedAt":"2026-01-15T01:37:54.260Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7084218859672546},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2601.08173","authors":[{"_id":"69683d0b0ac10a06522f698e","name":"Daocheng Fu","hidden":false},{"_id":"69683d0b0ac10a06522f698f","user":{"_id":"65827953d73d6402f7ae332d","avatarUrl":"/avatars/d57eae62171ece7a237eaf4ea938a31c.svg","isPro":false,"fullname":"Mei","user":"Jianbiao","type":"user"},"name":"Jianbiao Mei","status":"claimed_verified","statusLastChangedAt":"2026-01-15T15:03:34.293Z","hidden":false},{"_id":"69683d0b0ac10a06522f6990","user":{"_id":"66fa9fa56b620c614cdb1b57","avatarUrl":"/avatars/907c101ba4528de05d2ce4bb1ad82005.svg","isPro":false,"fullname":"Rong Wu","user":"Edaizi","type":"user"},"name":"Rong Wu","status":"claimed_verified","statusLastChangedAt":"2026-01-19T09:24:35.806Z","hidden":false},{"_id":"69683d0b0ac10a06522f6991","name":"Xuemeng Yang","hidden":false},{"_id":"69683d0b0ac10a06522f6992","name":"Jia Xu","hidden":false},{"_id":"69683d0b0ac10a06522f6993","name":"Ding Wang","hidden":false},{"_id":"69683d0b0ac10a06522f6994","name":"Pinlong Cai","hidden":false},{"_id":"69683d0b0ac10a06522f6995","name":"Yong Liu","hidden":false},{"_id":"69683d0b0ac10a06522f6996","name":"Licheng Wen","hidden":false},{"_id":"69683d0b0ac10a06522f6997","name":"Botian Shi","hidden":false}],"publishedAt":"2026-01-13T03:09:18.000Z","submittedOnDailyAt":"2026-01-14T22:36:15.771Z","title":"The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios","submittedOnDailyBy":{"_id":"64673506b990713c503079bc","avatarUrl":"/avatars/17396c835f1eeae00ec2972b6a24a2dd.svg","isPro":false,"fullname":"Fu","user":"fudaocheng","type":"user"},"summary":"The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce , a dynamic evaluation environment that simulates a \"trainee\" agent continuously exploring a novel setting. Unlike traditional benchmarks, evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv","upvotes":9,"discussionId":"69683d0b0ac10a06522f6998","githubRepo":"https://github.com/KnowledgeXLab/EvoEnv","githubRepoAddedBy":"user","ai_summary":"Dynamic evaluation environment for MLLMs addressing robustness challenges in real-world deployment through context-aware scheduling, active exploration, and continuous learning.","ai_keywords":["Multi-modal Large Language Models","dynamic task scheduling","active exploration","continuous learning","context-aware scheduling","prudent information acquisition","generalized strategies","rule-based tasks","production-oriented scenarios"],"githubStars":10,"organization":{"_id":"643cb0625fcffe09fb6ca688","name":"Fudan-University","fullname":"Fudan University","avatar":"https://cdn-uploads.huggingface.co/production/uploads/6437eca0819f3ab20d162e14/kWv0cGlAhAG3iNWVxowkJ.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64673506b990713c503079bc","avatarUrl":"/avatars/17396c835f1eeae00ec2972b6a24a2dd.svg","isPro":false,"fullname":"Fu","user":"fudaocheng","type":"user"},{"_id":"65827953d73d6402f7ae332d","avatarUrl":"/avatars/d57eae62171ece7a237eaf4ea938a31c.svg","isPro":false,"fullname":"Mei","user":"Jianbiao","type":"user"},{"_id":"66fa9fa56b620c614cdb1b57","avatarUrl":"/avatars/907c101ba4528de05d2ce4bb1ad82005.svg","isPro":false,"fullname":"Rong Wu","user":"Edaizi","type":"user"},{"_id":"66b9c431f1dfeeafaeadf272","avatarUrl":"/avatars/649c4375d0bbf3a47a03fe4d3702325b.svg","isPro":false,"fullname":"Tao Hu","user":"TaoTao0216","type":"user"},{"_id":"671905bf238d8cd549f0f740","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/671905bf238d8cd549f0f740/zmUNld9HqfFklMi2iWDrU.jpeg","isPro":false,"fullname":"jiaxin-ai(Sii)","user":"julyai","type":"user"},{"_id":"63082bb7bc0a2a5ee2253523","avatarUrl":"/avatars/6cf8d12d16d15db1070fbea89b5b3967.svg","isPro":false,"fullname":"Kuo-Hsin Tu","user":"dapumptu","type":"user"},{"_id":"6676179e4b1e661916d0c654","avatarUrl":"/avatars/a074b2c7baa49de9324329c752b49dfd.svg","isPro":false,"fullname":"Thomas Katraouras","user":"Tomk187","type":"user"},{"_id":"686db5d4af2b856fabbf13aa","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/6BjMv2LVNoqvbX8fQSTPI.png","isPro":false,"fullname":"V bbbb","user":"Bbbbbnnn","type":"user"},{"_id":"643df87f7cd64d872cb9fabd","avatarUrl":"/avatars/c53bfabcee08de448dde973915e8b31d.svg","isPro":false,"fullname":"Botian Shi","user":"friskit","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"643cb0625fcffe09fb6ca688","name":"Fudan-University","fullname":"Fudan University","avatar":"https://cdn-uploads.huggingface.co/production/uploads/6437eca0819f3ab20d162e14/kWv0cGlAhAG3iNWVxowkJ.png"}}">
Dynamic evaluation environment for MLLMs addressing robustness challenges in real-world deployment through context-aware scheduling, active exploration, and continuous learning.
AI-generated summary
The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce , a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. Unlike traditional benchmarks, evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv
The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce \method{}, a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. Unlike traditional benchmarks, \method{} evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv