Enhancing Software Engineering Through Closed-Loop Memory Optimization

• URL: http://arxiv.org/abs/2606.05646v1
• Date: Thu, 04 Jun 2026 03:17:21 GMT
• Title: Enhancing Software Engineering Through Closed-Loop Memory Optimization
• Abstract summary: We introduce ours, a closed-loop framework for memory augmentation in software engineering (SE) agents.<n>ours grounds memory utility in textitvalidated downstream impact, establishing utility as a task-agnostic textbf benchmark and an annotation-free textbfoptimization signal.<n>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.
• Score: 50.418699819003486
• License: http://creativecommons.org/licenses/by/4.0/
• 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 \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/}.

Related papers

• When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents [62.10623192614306]
  Extracting skills from past successes is critical for the efficient evolution of Large Language Model (LLM) agents.<n>We propose textbfBoundary-Aware Skill Memory (BASM), which augments each skill with explicit boundary fields.<n>BASM consistently outperforms success-distilled skill-memory baselines.
  arXiv  Detail & Related papers  (2026-08-23T10:16:06Z)
• Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory [7.254575731198877]
  On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights.<n>We propose sys, a single net-value-per-byte score that governs an agent's experience-memory lifecycle.
  arXiv  Detail & Related papers  (2026-06-23T19:42:07Z)
• AdaMem: Learning What to Remember for Personalized Long-Horizon LLM Agents [79.03892269184145]
  We argue that what is worth remembering is role-dependent, and propose textbfAdaMem (Adaptive Memory)<n>AdaMem improves QA accuracy by up to textbf+9.0% over the uniform Mem0 baseline while shrinking memory volume by textbf9%.
  arXiv  Detail & Related papers  (2026-06-19T06:35:52Z)
• NextMem: Towards Latent Factual Memory for LLM-based Agents [58.35585202907478]
  NextMem is a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory.<n>Extensive experiments demonstrate that NextMem achieves superior performance.
  arXiv  Detail & Related papers  (2026-02-26T14:35:27Z)
• AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents [26.029549618318086]
  We propose AriadneMem, a structured memory system that addresses problems in long-term dialogue.<n>We show that AriadneMem improves textbfMulti-Hop F1 by 15.2% and textbfAverage F1 by 9.0% over strong baselines.<n>By offloading reasoning to the graph layer, AriadneMem reduces textbftotal runtime by 77.8% using only textbf497 context tokens.
  arXiv  Detail & Related papers  (2026-02-05T22:19:31Z)
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution [52.76038908826961]
  We propose $textbfReMe$ ($textitRemember Me, Refine Me$) to bridge the gap between static storage and dynamic reasoning.<n>ReMe innovates across the memory lifecycle via three mechanisms: $textitmulti-faceted distillation$, which extracts fine-grained experiences.<n>Experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system.
  arXiv  Detail & Related papers  (2025-12-11T14:40:01Z)
• FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training [51.39495282347475]
  We introduce $textttFRUGAL$ ($textbfF$ull-$textbfR$ank $textbfU$pdates with $textbfG$r$textbfA$dient sp$textbfL$itting, a new memory-efficient optimization framework.<n>Our framework can be integrated with various low-rank update selection techniques, including GaLore and BAdam.
  arXiv  Detail & Related papers  (2024-11-12T14:41:07Z)
• Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage [19.54437582630868]
  textscInfant Agent integrates task-aware functions, operators, a hierarchical management system, and a memory retrieval mechanism. Using the textscInfant Agent, GPT-4o's accuracy on the SWE-bench-lite dataset rises from $mathbf0.33%$ to $mathbf30%$, and in the AIME-2024 mathematics competition, it increases GPT-4o's accuracy from $mathbf13.3%$ to $mathbf37%$.
  arXiv  Detail & Related papers  (2024-11-02T02:48:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.