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":"2026-02-05T01:42:40.369Z","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":0.727166473865509},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"698783b2dd11cee339c6ba0b","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":"2026-02-07T18:25:54.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"arXivLens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/swe-master-unleashing-the-potential-of-software-engineering-agents-via-post-training-3173-3b0ae72a\n- Executive Summary\n- Detailed Breakdown\n- Practical Applications","html":"

arXivLens breakdown of this paper 👉 https://arxivlens.com/PaperView/Details/swe-master-unleashing-the-potential-of-software-engineering-agents-via-post-training-3173-3b0ae72a

Executive Summary
Detailed Breakdown
Practical Applications

\n","updatedAt":"2026-02-07T18:25:54.512Z","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":0.7620295286178589},"editors":["avahal"],"editorAvatarUrls":["/avatars/743a009681d5d554c27e04300db9f267.svg"],"reactions":[{"reaction":"❤️","users":["daixuancheng"],"count":1}],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2602.03411","authors":[{"_id":"6982d3ec9084cb4f0ecb57ef","user":{"_id":"66163dc8c7f45b3f893ff40b","avatarUrl":"/avatars/801043dac0caae90bbca8c9d3e2e203b.svg","isPro":false,"fullname":"Song Huatong","user":"XXsongLALA","type":"user"},"name":"Huatong Song","status":"claimed_verified","statusLastChangedAt":"2026-02-10T09:08:02.704Z","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f0","name":"Lisheng Huang","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f1","name":"Shuang Sun","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f2","name":"Jinhao Jiang","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f3","name":"Ran Le","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f4","user":{"_id":"649e6761f9134a06ed1e0cea","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/649e6761f9134a06ed1e0cea/XNeKceE8xSwI0xWwWUwwJ.jpeg","isPro":false,"fullname":"Daixuan Cheng","user":"daixuancheng","type":"user"},"name":"Daixuan Cheng","status":"claimed_verified","statusLastChangedAt":"2026-02-04T12:27:42.035Z","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f5","name":"Guoxin Chen","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f6","name":"Yiwen Hu","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f7","name":"Zongchao Chen","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f8","name":"Wayne Xin Zhao","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57f9","name":"Yang Song","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57fa","name":"Tao Zhang","hidden":false},{"_id":"6982d3ec9084cb4f0ecb57fb","name":"Ji-Rong Wen","hidden":false}],"publishedAt":"2026-02-03T11:38:48.000Z","submittedOnDailyAt":"2026-02-04T02:51:43.510Z","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","submittedOnDailyBy":{"_id":"61b8405b516a20acdf3b85ff","avatarUrl":"/avatars/3d2eae7c163a80b73260087b05a4230b.svg","isPro":false,"fullname":"Jinhao Jiang","user":"Boru","type":"user"},"summary":"In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4\\% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8\\% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.","upvotes":37,"discussionId":"6982d3ec9084cb4f0ecb57fc","ai_summary":"SWE-Master presents a reproducible framework for developing software engineering agents through systematic optimization across multiple stages of agent development, achieving superior performance on software task resolution benchmarks.","ai_keywords":["post-training framework","teacher-trajectory synthesis","data curation","long-horizon SFT","RL with real execution feedback","inference framework design","SWE-bench Verified","resolve rate","test-time scaling","LLM-based environment feedback"],"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":"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":"63f06116f1a47aaea5bd497b","avatarUrl":"/avatars/7d99ffa59c4579599e852a0ffb261268.svg","isPro":false,"fullname":"Guoxin Chen","user":"GuoxinChen","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":"668fbc76611c65fd76c5ec43","avatarUrl":"/avatars/e0da0f1a2954861c85fa979dac14aff3.svg","isPro":false,"fullname":"Huang Lisheng","user":"lighitng","type":"user"},{"_id":"660b6b7895db9114e32e4ab8","avatarUrl":"/avatars/de151806ab5f3c0976d8fa0bcd4c1f63.svg","isPro":false,"fullname":"Shangguan Yike","user":"sgyk","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"},{"_id":"5e1058e9fcf41d740b69966d","avatarUrl":"/avatars/ce74839ba871f2b54313a670a233ba82.svg","isPro":false,"fullname":"Yongliang Shen","user":"tricktreat","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:2602.03411

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

Published on Feb 3

· Submitted by

Jinhao Jiang on Feb 4

RUC-AIBOX

Upvote

Authors:

Huatong Song ,

Daixuan Cheng ,

Abstract

SWE-Master presents a reproducible framework for developing software engineering agents through systematic optimization across multiple stages of agent development, achieving superior performance on software task resolution benchmarks.

AI-generated summary

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4\% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8\% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.