arXiv cs.AI· Xuehang Guo, Xingyao Wang, Zora Zhiruo Wang, Qingyun Wang, Graham Neubig, Heng Ji·· 15 小时前AI 评分35
MemOp：面向软件工程智能体的闭环记忆优化框架
Enhancing Software Engineering Through Closed-Loop Memory Optimization
AI 导读
MemOp 是一个面向软件工程智能体的闭环记忆增强框架，将记忆效用定义为可验证的下游影响，同时作为任务无关的评测基准和无标注优化信号。在四个基准、三种编程语言和两个 SE 智能体上，MemOp 使成功率最高提升 5.25%、解决效率提升 4.63%，部署成本降低至少 10.33%。该框架还展现出跨智能体、记忆骨干和优化算法的泛化性，训练出的记忆模型可迁移到未见过的编程语言和 SE 任务。
正文 · 原文
Abstract: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 MemOp, a closed-loop framework for memory augmentation in SE agents. MemOp 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}. Evaluating MemOp across four benchmarks, three programming languages, and two SE agents, under complementary \textit{single-episode} and \textit{cross-episode} memory augmentation, results demonstrate the \textbf{effectiveness} of MemOp, achieving absolute gains of up to $\uparrow5.25\%$ in success rate and $\uparrow4.63\%$ in resolve efficiency, while notably reducing deployment cost by $\geq10.33\%$. MemOp further exhibits \textbf{generalizability} across SE agents, memory backbones, and optimization algorithms, together with \textbf{transferability} of MemOp-trained memory model to unseen programming languages and SE activities. Our project page: this https URL.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.05646 [cs.SE] |
| (or arXiv:2606.05646v2 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2606.05646 arXiv-issued DOI via DataCite |
Submission history
From: Xuehang Guo [view email]
[v1]
Thu, 4 Jun 2026 03:17:21 UTC (18,294 KB)
[v2]
Mon, 26 Oct 2026 12:40:06 UTC (21,288 KB)
来源：arXiv cs.AI · arxiv.org