MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Simiao, Zhang, Li, Liu, Fang, Lian, Xiaoli, Liu, Yang, Zhu, Yinghao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914575389032448
author Liu, Simiao
Zhang, Li
Liu, Fang
Lian, Xiaoli
Liu, Yang
Zhu, Yinghao
author_facet Liu, Simiao
Zhang, Li
Liu, Fang
Lian, Xiaoli
Liu, Yang
Zhu, Yinghao
contents Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model (LLM)-based agents have recently shown promise for automated vulnerability repair (AVR), most existing systems still treat repair as a single generation step over the currently visible code context. As a result, they lack a persistent mechanism for reusing prior fixes or learning from failed validation attempts, which limits their effectiveness on complex, multi-file repair tasks. We present MemRepair, a memory-augmented agentic framework that formulates vulnerability repair as an iterative, experience-driven process. MemRepair combines three complementary memory layers, i.e., History-Fix, Security-Pattern, and Refinement-Trajectory memories, with a dynamic feedback-driven refinement loop. This design allows the agent to retrieve repository-specific repair conventions, apply reusable security defenses, and exploit prior "failure-to-success" trajectories to revise semantically invalid patches based on runtime evidence. We evaluate MemRepair on three representative repository-level vulnerability repair benchmarks: SEC-Bench, PatchEval (Python, Go, JavaScript), and the C++ subset of Multi-SWE-bench. MemRepair achieves state-of-the-art resolution rates of 58.0%, 58.2%, and 30.58%, respectively, outperforming strong general-purpose agents such as OpenHands and SWE-agent, as well as the specialized AVR tool InfCode-C++, while maintaining competitive repair cost. These results show that persistent, hierarchical repair memory can substantially improve the reliability of agentic vulnerability repair across diverse languages and repository settings.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17444
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
Liu, Simiao
Zhang, Li
Liu, Fang
Lian, Xiaoli
Liu, Yang
Zhu, Yinghao
Software Engineering
Artificial Intelligence
Computation and Language
Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model (LLM)-based agents have recently shown promise for automated vulnerability repair (AVR), most existing systems still treat repair as a single generation step over the currently visible code context. As a result, they lack a persistent mechanism for reusing prior fixes or learning from failed validation attempts, which limits their effectiveness on complex, multi-file repair tasks. We present MemRepair, a memory-augmented agentic framework that formulates vulnerability repair as an iterative, experience-driven process. MemRepair combines three complementary memory layers, i.e., History-Fix, Security-Pattern, and Refinement-Trajectory memories, with a dynamic feedback-driven refinement loop. This design allows the agent to retrieve repository-specific repair conventions, apply reusable security defenses, and exploit prior "failure-to-success" trajectories to revise semantically invalid patches based on runtime evidence. We evaluate MemRepair on three representative repository-level vulnerability repair benchmarks: SEC-Bench, PatchEval (Python, Go, JavaScript), and the C++ subset of Multi-SWE-bench. MemRepair achieves state-of-the-art resolution rates of 58.0%, 58.2%, and 30.58%, respectively, outperforming strong general-purpose agents such as OpenHands and SWE-agent, as well as the specialized AVR tool InfCode-C++, while maintaining competitive repair cost. These results show that persistent, hierarchical repair memory can substantially improve the reliability of agentic vulnerability repair across diverse languages and repository settings.
title MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
topic Software Engineering
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2605.17444