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 - ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
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":"2026-02-12T01:40:54.211Z","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":0.7255091667175293},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2602.06820","authors":[{"_id":"69894bebbeecc443208d25cc","name":"Dunwei Tu","hidden":false},{"_id":"69894bebbeecc443208d25cd","name":"Hongyan Hao","hidden":false},{"_id":"69894bebbeecc443208d25ce","user":{"_id":"65ced159d82f8d722c78e0cf","avatarUrl":"/avatars/a7121348e4fe77055533f14cda7f90b8.svg","isPro":false,"fullname":"Hansi Yang","user":"animawang","type":"user"},"name":"Hansi Yang","status":"claimed_verified","statusLastChangedAt":"2026-02-09T08:29:52.498Z","hidden":false},{"_id":"69894bebbeecc443208d25cf","name":"Yihao Chen","hidden":false},{"_id":"69894bebbeecc443208d25d0","name":"Yi-Kai Zhang","hidden":false},{"_id":"69894bebbeecc443208d25d1","name":"Zhikang Xia","hidden":false},{"_id":"69894bebbeecc443208d25d2","name":"Yu Yang","hidden":false},{"_id":"69894bebbeecc443208d25d3","name":"Yueqing Sun","hidden":false},{"_id":"69894bebbeecc443208d25d4","name":"Xingchen Liu","hidden":false},{"_id":"69894bebbeecc443208d25d5","name":"Furao Shen","hidden":false},{"_id":"69894bebbeecc443208d25d6","name":"Qi Gu","hidden":false},{"_id":"69894bebbeecc443208d25d7","name":"Hui Su","hidden":false},{"_id":"69894bebbeecc443208d25d8","name":"Xunliang Cai","hidden":false}],"publishedAt":"2026-02-06T16:05:55.000Z","submittedOnDailyAt":"2026-02-11T04:01:10.656Z","title":"ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training","submittedOnDailyBy":{"_id":"65ced159d82f8d722c78e0cf","avatarUrl":"/avatars/a7121348e4fe77055533f14cda7f90b8.svg","isPro":false,"fullname":"Hansi Yang","user":"animawang","type":"user"},"summary":"Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant limitations regarding environmental diversity and scalability. To address these challenges, we introduce ScaleEnv, a framework that constructs fully interactive environments and verifiable tasks entirely from scratch. Specifically, ScaleEnv ensures environment reliability through procedural testing, and guarantees task completeness and solvability via tool dependency graph expansion and executable action verification. By enabling agents to learn through exploration within ScaleEnv, we demonstrate significant performance improvements on unseen, multi-turn tool-use benchmarks such as τ^2-Bench and VitaBench, highlighting strong generalization capabilities. Furthermore, we investigate the relationship between increasing number of domains and model generalization performance, providing empirical evidence that scaling environmental diversity is critical for robust agent learning.","upvotes":13,"discussionId":"69894bebbeecc443208d25d9","ai_summary":"ScaleEnv framework generates interactive environments from scratch to improve agent generalization through diverse domain scaling and verified task completion.","ai_keywords":["generalist agents","interactive environments","self-exploration","procedural testing","tool dependency graph expansion","executable action verification","multi-turn tool-use benchmarks","τ²-Bench","VitaBench","model generalization"],"organization":{"_id":"68b28d79a176a9beb30d2049","name":"meituan-longcat","fullname":"LongCat","avatar":"https://cdn-uploads.huggingface.co/production/uploads/68a2a29ab9d4c5698e02c747/CDCAx7X7rXDt7xjI-DoxG.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65ffa01757cc48d9d34c6680","avatarUrl":"/avatars/82802c540395ae36ec00181453b5df42.svg","isPro":false,"fullname":"kk","user":"zhangyikai","type":"user"},{"_id":"659b9bce28676374f3221fee","avatarUrl":"/avatars/008520e73fe79db58250f9038b5cfd68.svg","isPro":false,"fullname":"HHY","user":"Jaderoof","type":"user"},{"_id":"66f547c5405af2cd3256ba27","avatarUrl":"/avatars/fc52bac1785191af0eb9a1d108c4397e.svg","isPro":false,"fullname":"JP Zhu","user":"JPZhu","type":"user"},{"_id":"68a01c2a4b11fd9a48c8aea3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/FIirWWMrEYZ-IOQnVD9YF.png","isPro":false,"fullname":"Dunwei Tu","user":"breakerAI","type":"user"},{"_id":"69894f1be44614820102c160","avatarUrl":"/avatars/342448fc997ed78d37273e270f3c91d0.svg","isPro":false,"fullname":"niuchenlong","user":"NiuChenlong","type":"user"},{"_id":"698950ee004a03e09ff79c7a","avatarUrl":"/avatars/516a91aeefe19d0128b2e5b9760ca8d5.svg","isPro":false,"fullname":"young","user":"cayde-six","type":"user"},{"_id":"69895163d4735141e87126c7","avatarUrl":"/avatars/3a5f5c4991a3bbbd3cb7b52cd7fadcf9.svg","isPro":false,"fullname":"feyy","user":"feyyli","type":"user"},{"_id":"66ab2a0f3884d7688c40e3f3","avatarUrl":"/avatars/a6d71d41d79fef63ddcf8f5dd0e335ea.svg","isPro":false,"fullname":"Xingchen Liu","user":"mm1106","type":"user"},{"_id":"65ced159d82f8d722c78e0cf","avatarUrl":"/avatars/a7121348e4fe77055533f14cda7f90b8.svg","isPro":false,"fullname":"Hansi Yang","user":"animawang","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"63c1699e40a26dd2db32400d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63c1699e40a26dd2db32400d/3N0-Zp8igv8-52mXAdiiq.jpeg","isPro":false,"fullname":"Chroma","user":"Chroma111","type":"user"},{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"68b28d79a176a9beb30d2049","name":"meituan-longcat","fullname":"LongCat","avatar":"https://cdn-uploads.huggingface.co/production/uploads/68a2a29ab9d4c5698e02c747/CDCAx7X7rXDt7xjI-DoxG.png"}}">
ScaleEnv framework generates interactive environments from scratch to improve agent generalization through diverse domain scaling and verified task completion.
AI-generated summary
Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant limitations regarding environmental diversity and scalability. To address these challenges, we introduce ScaleEnv, a framework that constructs fully interactive environments and verifiable tasks entirely from scratch. Specifically, ScaleEnv ensures environment reliability through procedural testing, and guarantees task completeness and solvability via tool dependency graph expansion and executable action verification. By enabling agents to learn through exploration within ScaleEnv, we demonstrate significant performance improvements on unseen, multi-turn tool-use benchmarks such as τ^2-Bench and VitaBench, highlighting strong generalization capabilities. Furthermore, we investigate the relationship between increasing number of domains and model generalization performance, providing empirical evidence that scaling environmental diversity is critical for robust agent learning.
We introduce ScaleEnv, a framework that constructs fully interactive environments and verifiable tasks entirely from scratch. By enabling agents to learn through exploration within ScaleEnv, we demonstrate significant performance improvements on unseen, multi-turn tool-use benchmarks such as $\tau^2$-Bench and VitaBench, highlighting strong generalization capabilities.