Socratic-SWE is a self-evolution framework for coding agents that distills historical solving traces into structured skills, enabling the generation of targeted tasks to improve software engineering performance.</p>\n","updatedAt":"2026-06-08T01:53:08.797Z","author":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","fullname":"taesiri","name":"taesiri","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":312,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9049251079559326},"editors":["taesiri"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.07412","authors":[{"_id":"6a26207be4c258a029491f9d","name":"Chuan Xiao","hidden":false},{"_id":"6a26207be4c258a029491f9e","name":"Zhengbo Jiao","hidden":false},{"_id":"6a26207be4c258a029491f9f","name":"Shaobo Wang","hidden":false},{"_id":"6a26207be4c258a029491fa0","name":"Wei Wang","hidden":false},{"_id":"6a26207be4c258a029491fa1","name":"Bing Zhao","hidden":false},{"_id":"6a26207be4c258a029491fa2","name":"Hu Wei","hidden":false},{"_id":"6a26207be4c258a029491fa3","name":"Linfeng Zhang","hidden":false},{"_id":"6a26207be4c258a029491fa4","name":"Lin Qu","hidden":false}],"publishedAt":"2026-06-05T00:00:00.000Z","submittedOnDailyAt":"2026-06-08T00:00:00.000Z","title":"Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills","submittedOnDailyBy":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user","name":"taesiri"},"summary":"LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks. Existing synthetic data methods typically create tasks through fixed mutation or bug-injection procedures, making the resulting distributions largely independent of the agent's own weaknesses and training progress. We introduce Socratic-SWE, a closed-loop self-evolution framework that reuses the agent's historical solving traces as a source of training signal. Rather than treating traces only as evidence for reward computation, Socratic-SWE distills them into structured agent skills that summarize recurring failures and effective repair patterns. These skills then guide the generation of targeted repair tasks in real repositories. Candidate tasks are checked through execution-based validation and scored with a solver-gradient alignment reward, so that the retained tasks are both verifiable and useful for improving the Solver. The updated Solver produces new traces, enabling the task curriculum to adapt over successive rounds. Across SWE-bench Verified, SWE-bench Lite, SWE-bench Pro, and Terminal-Bench 2.0, Socratic-SWE consistently improves over self-evolving baselines under the same compute budget, reaching 50.40% on SWE-bench Verified after three iterations. These results suggest that solving traces can serve as a scalable substrate for self-evolving SWE agents.","upvotes":1,"discussionId":"6a26207be4c258a029491fa5","ai_summary":"Socratic-SWE enables self-evolving software engineering agents by leveraging historical solving traces to generate targeted repair tasks that improve agent performance through iterative refinement.","ai_keywords":["LLM-driven software engineering agents","synthetic data methods","fixed mutation","bug-injection procedures","closed-loop self-evolution framework","historical solving traces","structured agent skills","repair patterns","execution-based validation","solver-gradient alignment reward","task curriculum","self-evolving baselines","SWE-bench Verified","SWE-bench Lite","SWE-bench Pro","Terminal-Bench 2.0"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"68355c5ec0003bc40230b3f2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/68355c5ec0003bc40230b3f2/fJjAPFtmAJskQJqxWUb-T.jpeg","isPro":false,"fullname":"jasmineWang","user":"Jessamine","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0}">

Cite arxiv.org/abs/2606.07412 in a model README.md to link it from this page.

Cite arxiv.org/abs/2606.07412 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2606.07412 in a Space README.md to link it from this page.