# Enhancing Software Engineering Through Closed-Loop Memory Optimization

arXiv: https://arxiv.org/abs/2606.05646 · HTML: https://mlsanity.com/paper/2606.05646/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation](https://mlsanity.com/paper/2409.05591/) (2024)
- [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024)
- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (2024)
- [MemInsight: Autonomous Memory Augmentation for LLM Agents](https://mlsanity.com/paper/2503.21760/) (2025)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [Towards Lifelong Dialogue Agents via Timeline-based Memory Management](https://mlsanity.com/paper/2406.10996/) (2024)
- [M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions](https://mlsanity.com/paper/2405.16420/) (2024)
- [Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations](https://mlsanity.com/paper/2402.11975/) (2024)
- [CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory](https://mlsanity.com/paper/2402.13449/) (2024)
- [Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly](https://mlsanity.com/paper/2408.01866/) (2024)
- [Improving Code Localization with Repository Memory](https://mlsanity.com/paper/2510.01003/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Structurally Aligned Subtask-Level Memory for Software Engineering Agents](https://mlsanity.com/paper/2602.21611/) (2026)
- [MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences](https://mlsanity.com/paper/2601.06789/) (2026)
- [From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents](https://mlsanity.com/paper/2505.23422/) (2025)
- [TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG](https://mlsanity.com/paper/2412.05447/) (2024)
- [ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry](https://mlsanity.com/paper/2506.21098/) (2025)
- [Model Editing with Graph-Based External Memory](https://mlsanity.com/paper/2505.18343/) (2025)

## Abstract (arXiv)

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 textitmemory 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 textitvalidated downstream impact, establishing utility as both a task-agnostic evaluation benchmark and an annotation-free optimization signal. Through complementary evaluation on textitsingle-episode and textitcross-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 ≥9.79%. Our project page: hrefhttps://xhguo7.github.io/MemOp/https://xhguo7.github.io/MemOp/.