让编程智能体学会通用技能，避免过拟合，提升代码任务表现。
Learning Globally Reusable Skills for Coding Agents
- 构建技能关系图，全局优化技能间兼容性与泛化能力。
- 通过聚类抽象和回放验证，使技能更新更稳定、可复用。
- 适合希望提升代码生成与缺陷检测能力的研究者和工程师。
自动化技能演化使大型语言模型（LLM）智能体能在无需昂贵重训练的情况下持续改进。然而，现有方法通常将技能演化视为一系列局部更新，忽视了技能间的关联，常导致过拟合的更新，难以跨任务泛化。我们提出 GSE，一种全局化的技能演化框架，联合优化技能兼容性与泛化能力。为保持技能库的一致性，GSE维护一个技能关系图（SRG），显式建模并协同演化技能间关系。为提升泛化能力，GSE采用基于聚类的技能合并，从局部更新中抽象出可复用的能力，并使用回放驱动的验证防止过拟合与行为退化。我们在两个典型软件工程任务上评估：缺陷暴露测试生成与误报漏洞报告过滤。在两个先进编码代理 OpenHands 与 mini-SWE-agent 上，GSE 均显著提升精确率、召回率与 F1-score。相比现有演化技术，测试生成任务中精确率提升 6.1%~34.1%，召回率提升 31.8%~180.0%；误报过滤任务中精确率提升 15.4%~96.4%，召回率提升 13.1%~19.8%。在内部工业级代理部署中，F1-score 提升达 61.4%，证明 GSE 在演化高效技能方面的有效性与泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。