让编程助手学会总结经验，自动优化记忆，提升效率与成功率。
Enhancing Software Engineering Through Closed-Loop Memory Optimization
- 以实际效果定义记忆价值，实现无标注的自我优化
- 跨任务记忆提升5.25%成功率，修复效率提高4.63%，节省超9.79%计算成本
- 适合想让代码助手持续进化、减少重复错误的研究者和开发者
大型语言模型（LLMs）已赋能强大的软件工程（SE）智能体，使其能处理复杂代码库并解决现实问题。然而，这些智能体仍为片段式行为：无法保留、优化和复用经验，反复从头构建上下文并重复类似错误。即使有记忆支持，也缺乏一种通用、任务无关的「记忆效用」机制，导致难以严格评估或在不同智能体间泛化。为此，我们提出 extit{ours}，一个面向软件工程智能体的闭环记忆增强框架。该框架将记忆效用建立在「可验证的下游影响」之上，使效用同时成为任务无关的评估基准与无标注的优化信号。在单次任务与跨任务记忆增强上的对比实验表明， extit{ours} 在多种场景下均显著提升智能体表现，成功率达最高提升5.25%，修复效率提升4.63%，计算开销降低≥9.79%。
原文摘要 · Abstract (English)
Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues. However, these agents remain fundamentally episodic: they fail to retain, refine, and reuse experiences across tasks, repeatedly reconstructing context from scratch and reproducing similar mistakes. Even with memory support, they offer no remedy for the absence of a principled, task-agnostic \textit{memory utility}, making them difficult to evaluate rigorously or generalize across agents and settings. To tackle these limitations, we introduce \ours, a closed-loop framework for memory augmentation in SE agents. \ours grounds memory utility in \textit{validated downstream impact}, establishing utility as both a task-agnostic \textbf{evaluation benchmark} and an annotation-free \textbf{optimization signal}. Through complementary evaluation on \textit{single-episode} and \textit{cross-episode} memory augmentation, results demonstrate that \ours consistently improves SE agents across settings, achieving absolute gains of up to $\uparrow5.25\%$ in success rate and $\uparrow4.63\%$ in resolve efficiency, while substantially reducing computational cost by $\geq9.79\%$. Our project page: \href{https://xhguo7.github.io/MemOp/}{https://xhguo7.github.io/MemOp/}.
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。