Kimi-Dev: Agentless Training as Skill Prior for SWE-agents
Department of Computer Science and Technology, Tsinghua University · Tsinghua University, Moonshot AI · Peking University · University of the Chinese Academy of Sciences · Moonshot AI · Beijing University of Posts and Telecommunications · nudt · NUS · University of Massachusetts at Amherst · ByteDance · Tsinghua University · Tsinghua University, Tsinghua University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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.