Socratic-SWE：通过轨迹衍生智能体技能实现自我进化的编码智能体
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
AI总结：
提出Socratic-SWE闭环自进化框架，通过将智能体历史求解轨迹蒸馏为结构化技能，生成针对性修复任务，实现编码智能体的持续自我改进。
摘要：
基于LLM的软件工程智能体已成为现实世界语言模型能力的核心测试平台，但其训练仍受限于高质量SWE任务的可用性。现有的合成数据方法通常通过固定突变或漏洞注入程序创建任务，导致生成的任务分布很大程度上独立于智能体自身的弱点和训练进度。我们提出Socratic-SWE，一个闭环自进化框架，将智能体的历史求解轨迹重新用作训练信号的来源。Socratic-SWE不仅将轨迹视为奖励计算的证据，还将其蒸馏为结构化的智能体技能，总结重复出现的失败模式和有效的修复模式。这些技能随后指导在真实仓库中生成针对性的修复任务。候选任务通过基于执行的验证进行检查，并使用求解器梯度对齐奖励进行评分，从而保留的任务既可验证又有助于改进求解器。更新后的求解器产生新的轨迹，使任务课程能够在连续轮次中自适应。在SWE-bench Verified、SWE-bench Lite、SWE-bench Pro和Terminal-Bench 2.0上，Socratic-SWE在相同计算预算下持续优于自我进化的基线，经过三次迭代后在SWE-bench Verified上达到50.40%。这些结果表明，求解轨迹可以作为自我进化SWE智能体的可扩展基础。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
