Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2026-02-05T01:40:23.442Z","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":317,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7323435544967651},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"6987838d786407d0593177c3","author":{"_id":"65243980050781c16f234f1f","avatarUrl":"/avatars/743a009681d5d554c27e04300db9f267.svg","fullname":"Avi","name":"avahal","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false},"createdAt":"2026-02-07T18:25:17.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"arXivLens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/swe-world-building-software-engineering-agents-in-docker-free-environments-358-8688992d\n- Executive Summary\n- Detailed Breakdown\n- Practical Applications","html":"

arXivLens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/swe-world-building-software-engineering-agents-in-docker-free-environments-358-8688992d

Executive Summary
Detailed Breakdown
Practical Applications

\n","updatedAt":"2026-02-07T18:25:17.574Z","author":{"_id":"65243980050781c16f234f1f","avatarUrl":"/avatars/743a009681d5d554c27e04300db9f267.svg","fullname":"Avi","name":"avahal","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":3,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7452067136764526},"editors":["avahal"],"editorAvatarUrls":["/avatars/743a009681d5d554c27e04300db9f267.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2602.03419","authors":[{"_id":"6982d38d9084cb4f0ecb57df","name":"Shuang Sun","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e0","user":{"_id":"66163dc8c7f45b3f893ff40b","avatarUrl":"/avatars/801043dac0caae90bbca8c9d3e2e203b.svg","isPro":false,"fullname":"Song Huatong","user":"XXsongLALA","type":"user"},"name":"Huatong Song","status":"claimed_verified","statusLastChangedAt":"2026-02-10T09:08:05.057Z","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e1","name":"Lisheng Huang","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e2","name":"Jinhao Jiang","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e3","name":"Ran Le","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e4","name":"Zhihao Lv","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e5","name":"Zongchao Chen","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e6","name":"Yiwen Hu","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e7","name":"Wenyang Luo","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e8","name":"Wayne Xin Zhao","hidden":false},{"_id":"6982d38d9084cb4f0ecb57e9","name":"Yang Song","hidden":false},{"_id":"6982d38d9084cb4f0ecb57ea","name":"Hongteng Xu","hidden":false},{"_id":"6982d38d9084cb4f0ecb57eb","name":"Tao Zhang","hidden":false},{"_id":"6982d38d9084cb4f0ecb57ec","name":"Ji-Rong Wen","hidden":false}],"publishedAt":"2026-02-03T11:44:39.000Z","submittedOnDailyAt":"2026-02-04T02:52:59.734Z","title":"SWE-World: Building Software Engineering Agents in Docker-Free Environments","submittedOnDailyBy":{"_id":"61b8405b516a20acdf3b85ff","avatarUrl":"/avatars/3d2eae7c163a80b73260087b05a4230b.svg","isPro":false,"fullname":"Jinhao Jiang","user":"Boru","type":"user"},"summary":"Recent advances in large language models (LLMs) have enabled software engineering agents to tackle complex code modification tasks. Most existing approaches rely on execution feedback from containerized environments, which require dependency-complete setup and physical execution of programs and tests. While effective, this paradigm is resource-intensive and difficult to maintain, substantially complicating agent training and limiting scalability. We propose SWE-World, a Docker-free framework that replaces physical execution environments with a learned surrogate for training and evaluating software engineering agents. SWE-World leverages LLM-based models trained on real agent-environment interaction data to predict intermediate execution outcomes and final test feedback, enabling agents to learn without interacting with physical containerized environments. This design preserves the standard agent-environment interaction loop while eliminating the need for costly environment construction and maintenance during agent optimization and evaluation. Furthermore, because SWE-World can simulate the final evaluation outcomes of candidate trajectories without real submission, it enables selecting the best solution among multiple test-time attempts, thereby facilitating effective test-time scaling (TTS) in software engineering tasks. Experiments on SWE-bench Verified demonstrate that SWE-World raises Qwen2.5-Coder-32B from 6.2\\% to 52.0\\% via Docker-free SFT, 55.0\\% with Docker-free RL, and 68.2\\% with further TTS. The code is available at https://github.com/RUCAIBox/SWE-World","upvotes":39,"discussionId":"6982d38d9084cb4f0ecb57ed","ai_summary":"A Docker-free framework replaces physical execution environments with learned surrogates for training software engineering agents, enabling efficient training and test-time scaling without costly container setup.","ai_keywords":["large language models","software engineering agents","Docker-free framework","surrogate models","agent-environment interaction","test-time scaling","SWE-bench","Qwen2.5-Coder-32B"],"organization":{"_id":"6704ef33935b1a7c59795566","name":"RUC-AIBOX","fullname":"RUC-AIBOX","avatar":"https://cdn-uploads.huggingface.co/production/uploads/61b8405b516a20acdf3b85ff/Q3_mJHjNqZYfArFl1ZpAL.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65c747f1bbc318a59eceb452","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65c747f1bbc318a59eceb452/W5ERLsLFmwhbt-blcNslJ.jpeg","isPro":false,"fullname":"Shuang Sun","user":"SNHE","type":"user"},{"_id":"61b8405b516a20acdf3b85ff","avatarUrl":"/avatars/3d2eae7c163a80b73260087b05a4230b.svg","isPro":false,"fullname":"Jinhao Jiang","user":"Boru","type":"user"},{"_id":"685a6d13c3a4f905b814bc93","avatarUrl":"/avatars/2e2deb7b6af6cc4dbdbb1e9d0680e0a5.svg","isPro":false,"fullname":"sun","user":"SunSec","type":"user"},{"_id":"66e006bb0b027148713f9a51","avatarUrl":"/avatars/841418391cb971de02f3cfc195a0ed0a.svg","isPro":false,"fullname":"HT","user":"haoyut","type":"user"},{"_id":"66e03eace17fb5ff054b7686","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66e03eace17fb5ff054b7686/PpSV0Qo5lwTyxIZMp57xq.jpeg","isPro":false,"fullname":"Xiaoxi Li","user":"lixiaoxi45","type":"user"},{"_id":"66163dc8c7f45b3f893ff40b","avatarUrl":"/avatars/801043dac0caae90bbca8c9d3e2e203b.svg","isPro":false,"fullname":"Song Huatong","user":"XXsongLALA","type":"user"},{"_id":"674476e821e39628723f13ad","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/7iUE9VSdvuX979_vERXpI.png","isPro":false,"fullname":"mfzzzzzz","user":"mfzzzzzz","type":"user"},{"_id":"61d78857a21a9b49c7e8e4a9","avatarUrl":"/avatars/c7e7f84cad775be2d13fab8530bf21f5.svg","isPro":false,"fullname":"Yifan Du","user":"Richard1999","type":"user"},{"_id":"63f06116f1a47aaea5bd497b","avatarUrl":"/avatars/7d99ffa59c4579599e852a0ffb261268.svg","isPro":false,"fullname":"Guoxin Chen","user":"GuoxinChen","type":"user"},{"_id":"660b6b7895db9114e32e4ab8","avatarUrl":"/avatars/de151806ab5f3c0976d8fa0bcd4c1f63.svg","isPro":false,"fullname":"Shangguan Yike","user":"sgyk","type":"user"},{"_id":"668fbc76611c65fd76c5ec43","avatarUrl":"/avatars/e0da0f1a2954861c85fa979dac14aff3.svg","isPro":false,"fullname":"Huang Lisheng","user":"lighitng","type":"user"},{"_id":"6317419f3eb2544b62389a79","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6317419f3eb2544b62389a79/8oU90du902ATtBPYCcLFK.jpeg","isPro":false,"fullname":"Ivan Hu","user":"IvanHU","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"6704ef33935b1a7c59795566","name":"RUC-AIBOX","fullname":"RUC-AIBOX","avatar":"https://cdn-uploads.huggingface.co/production/uploads/61b8405b516a20acdf3b85ff/Q3_mJHjNqZYfArFl1ZpAL.png"}}">

Papers

arxiv:2602.03419

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Published on Feb 3

· Submitted by

Jinhao Jiang on Feb 4

RUC-AIBOX

Upvote

Authors:

Huatong Song ,

Abstract

A Docker-free framework replaces physical execution environments with learned surrogates for training software engineering agents, enabling efficient training and test-time scaling without costly container setup.

AI-generated summary

Recent advances in large language models (LLMs) have enabled software engineering agents to tackle complex code modification tasks. Most existing approaches rely on execution feedback from containerized environments, which require dependency-complete setup and physical execution of programs and tests. While effective, this paradigm is resource-intensive and difficult to maintain, substantially complicating agent training and limiting scalability. We propose SWE-World, a Docker-free framework that replaces physical execution environments with a learned surrogate for training and evaluating software engineering agents. SWE-World leverages LLM-based models trained on real agent-environment interaction data to predict intermediate execution outcomes and final test feedback, enabling agents to learn without interacting with physical containerized environments. This design preserves the standard agent-environment interaction loop while eliminating the need for costly environment construction and maintenance during agent optimization and evaluation. Furthermore, because SWE-World can simulate the final evaluation outcomes of candidate trajectories without real submission, it enables selecting the best solution among multiple test-time attempts, thereby facilitating effective test-time scaling (TTS) in software engineering tasks. Experiments on SWE-bench Verified demonstrate that SWE-World raises Qwen2.5-Coder-32B from 6.2\% to 52.0\% via Docker-free SFT, 55.0\% with Docker-free RL, and 68.2\% with further TTS. The code is available at https://github.com/RUCAIBox/SWE-World