SkillForge：面向项目特定问题解决的自蒸馏智能体
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
SkillForge是一种主动从代码库获取项目特定知识的自蒸馏框架，通过合成问题蒸馏技能，可提升LLM智能体解决特定代码库软件问题的性能。
中文摘要 AI 辅助
基于大语言模型（LLM）的智能体在自动化软件问题解决方面展现出卓越能力，但它们往往因缺乏项目特定知识而难以解决特定代码库中的问题。现有的自进化方法从代码库历史或在线修复轨迹中获取此类知识，要么依赖可用的历史问题解决信号，要么会产生巨大的单问题测试时探索成本。在本文中，我们提出SkillForge，一种主动从代码库本身获取项目特定知识的自蒸馏框架。SkillForge不会等待真实问题暴露项目特定知识缺口，而是通过重新实现代码库中测试覆盖的核心功能来合成项目特定问题。通过解决这些合成问题，SkillForge将可复用的项目特定知识蒸馏为基于实体的技能，并将它们与相关的代码库实体关联起来，以便未来解决问题。使用开源和闭源模型进行的大量实验表明，SkillForge相比强基线持续提升了问题解决性能。这些结果证明，在解决真实问题之前主动获取项目特定知识可显著改善下游软件问题解决效果。
英文摘要
Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resolution, yet they often struggle to resolve issues in a specific repository because they lack project-specific knowledge. Existing self-evolving approaches acquire such knowledge from repository history or online repair trajectories, but they either depend on available historical issue-resolution signals or incur substantial per-issue test-time exploration cost. In this paper, we propose SkillForge, a self-distillation framework that proactively acquires project-specific knowledge from the repository itself. Instead of waiting for real issues to expose project-specific knowledge gaps, SkillForge synthesizes project-specific issues by re-implementing test-covered core functionalities of the repository. By resolving these synthetic issues, SkillForge distills reusable project-specific knowledge into entity-grounded skills and associates them with relevant repository entities for future issue resolution. Extensive experiments using both open-source and closed-source models show that SkillForge consistently improves issue resolution performance over strong baselines. These results demonstrate that proactively acquiring project-specific knowledge before solving real issues substantially improves downstream software issue resolution.
