SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution

2026-08-19

AI Summary

为解决基于大型语言模型的代理在处理特定项目问题时缺乏专业知识的问题，提出SkillForge框架，通过合成项目特有问题主动获取并提炼项目知识，提高问题解决效率。

Abstract

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.

Problem

• Large language model
• Project-specific knowledge
• Software issue resolution

Innovation

• self-distillation
• project-specific knowledge
• synthetic issues
• entity-grounded skills