mlsanityData to 7 Oct 2026

Enhancing Software Engineering Through Closed-Loop Memory Optimization

arXiv 2606.05646 ↗First posted 4 Jun 2026cs.SE cs.AIcited by 0

Not on the map. Why?

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/.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 34 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

29 of 34 references.

References · 29

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  6. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  7. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  8. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 278
  9. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 211
  10. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 200
  11. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 132
  12. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 118
17 more
  1. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  2. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  3. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 84
  4. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentscited by 60
  5. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 50
  6. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  7. 2024Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversationscited by 36
  8. 2024CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memorycited by 24
  9. 2024Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlesslycited by 23
  10. 2025Improving Code Localization with Repository Memorycited by 19
  11. 2025A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic Systemcited by 15
  12. 2026Structurally Aligned Subtask-Level Memory for Software Engineering Agentscited by 11
  13. 2026MemGovern: Enhancing Code Agents through Learning from Governed Human Experiencescited by 10
  14. 2025From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agentscited by 4
  15. 2025ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industrycited by 3
  16. 2024TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAGcited by 2
  17. 2025Model Editing with Graph-Based External Memorycited by 2

Built on by

Not cited yet.