发表机构
Tianjin University; Tsinghua University（天津大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对编码智能体技能进化的过拟合与泛化问题，提出GSE框架，通过技能关系图、聚类整合与回放验证优化，在多个编码任务与智能体上实现性能提升，效果显著。
AI 中文摘要
自动化技能进化使大语言模型（LLM）智能体无需昂贵的重新训练即可持续改进，但现有方法通常将技能进化视为一系列局部更新，忽略技能间的关系，且常产生过拟合的技能更新，无法跨任务泛化。我们提出GSE，一种全球化技能进化框架，联合优化技能兼容性与技能泛化能力。为保持技能库的一致性，GSE维护一个技能关系图（Skill Relation Graph，SRG），该图显式建模技能间的关系并协同进化。为提升泛化能力，GSE执行基于聚类的技能整合，从局部更新中抽象出可复用能力，并采用回放驱动验证以防止过拟合与行为退化。我们在两个代表性软件工程任务上评估GSE：漏洞暴露测试生成与误报漏洞报告过滤。在两个最先进的编码智能体OpenHands和mini-SWE-agent上，GSE始终取得最佳的精度、召回率与F1分数。与现有进化技术相比，GSE在测试生成任务上将精度与召回率分别提升6.1%~34.1%与31.8%~180.0%，在误报过滤任务上分别提升15.4%~96.4%与13.1%~19.8%；在一个内部工业智能体上部署后，F1分数进一步提升61.4%，证明了GSE进化有效技能的有效性与泛化性。
英文摘要
Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches typically treat skill evolution as a sequence of local updates, overlooking relationships among skills and often producing overfitted skill updates that fail to generalize across tasks. We propose GSE, a globalized skill evolution framework that jointly optimizes skill compatibility and skill generalization. To preserve consistency across the skill bank, GSE maintains a Skill Relation Graph (SRG) that explicitly models and co-evolves inter-skill relationships. To improve generalization, GSE performs cluster-based skill consolidation to abstract reusable capabilities from local updates and employs replay-driven verification to prevent overfitting and behavioral regressions. We evaluate GSE on two representative software engineering tasks: bug-revealing test generation and false-positive bug report filtering. Across two state-of-the-art coding agents, OpenHands and mini-SWE-agent, GSE consistently achieves the best precision, recall, and F1-score. Compared with existing evolution techniques, GSE improves precision and recall by 6.1%~34.1% and 31.8%~180.0% for test generation, and by 15.4%~96.4% and 13.1%~19.8% for false-positive filtering. Deployment on an internal industrial agent further yields a 61.4% improvement in F1-score, demonstrating the effectiveness and generalizability of GSE for evolving effective skills.
