{"ID":2864524,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23045","arxiv_id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","abstract":"Large Language Models (LLMs) are increasingly applied to software engineering (SWE), with SWE-bench as a key benchmark. Solutions are split into SWE-Agent frameworks with multi-turn interactions and workflow-based Agentless methods with single-turn verifiable steps. We argue these paradigms are not mutually exclusive: reasoning-intensive Agentless training induces skill priors, including localization, code edit, and self-reflection that enable efficient and effective SWE-Agent adaptation. In this work, we first curate the Agentless training recipe and present Kimi-Dev, an open-source SWE LLM achieving 60.4\\% on SWE-bench Verified, the best among workflow approaches. With additional SFT adaptation on 5k publicly-available trajectories, Kimi-Dev powers SWE-Agents to 48.6\\% pass@1, on par with that of Claude 3.5 Sonnet (241022 version). These results show that structured skill priors from Agentless training can bridge workflow and agentic frameworks for transferable coding agents.","short_abstract":"Large Language Models (LLMs) are increasingly applied to software engineering (SWE), with SWE-bench as a key benchmark. Solutions are split into SWE-Agent frameworks with multi-turn interactions and workflow-based Agentless methods with single-turn verifiable steps. We argue these paradigms are not mutually exclusive:...","url_abs":"https://arxiv.org/abs/2509.23045","url_pdf":"https://arxiv.org/pdf/2509.23045v3","authors":"[\"Zonghan Yang\",\"Shengjie Wang\",\"Kelin Fu\",\"Wenyang He\",\"Weimin Xiong\",\"Yibo Liu\",\"Yibo Miao\",\"Bofei Gao\",\"Yejie Wang\",\"Yingwei Ma\",\"Yanhao Li\",\"Yue Liu\",\"Zhenxing Hu\",\"Kaitai Zhang\",\"Shuyi Wang\",\"Huarong Chen\",\"Flood Sung\",\"Yang Liu\",\"Yang Gao\",\"Zhilin Yang\",\"Tianyu Liu\"]","published":"2025-09-27T01:49:13Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}