AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Charoenwet, Wachiraphan, Tantithamthavorn, Kla, Thongtanunam, Patanamon, Lin, Hong Yi, Jeong, Minwoo, Wu, Ming
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917224987492352
author Charoenwet, Wachiraphan
Tantithamthavorn, Kla
Thongtanunam, Patanamon
Lin, Hong Yi
Jeong, Minwoo
Wu, Ming
author_facet Charoenwet, Wachiraphan
Tantithamthavorn, Kla
Thongtanunam, Patanamon
Lin, Hong Yi
Jeong, Minwoo
Wu, Ming
contents Secure code review is critical at the pre-commit stage, where vulnerabilities must be caught early under tight latency and limited-context constraints. Existing SAST-based checks are noisy and often miss immature, context-dependent vulnerabilities, while standalone Large Language Models (LLMs) are constrained by context windows and lack explicit tool use. Agentic AI, which combine LLMs with autonomous decision-making, tool invocation, and code navigation, offer a promising alternative, but their effectiveness for pre-commit secure code review is not yet well understood. In this work, we introduce AgenticSCR, an agentic AI for secure code review for detecting immature vulnerabilities during the pre-commit stage, augmented by security-focused semantic memories. Using our own curated benchmark of immature vulnerabilities, tailored to the pre-commit secure code review, we empirically evaluate how accurate is our AgenticSCR for localizing, detecting, and explaining immature vulnerabilities. Our results show that AgenticSCR achieves at least 153% relatively higher percentage of correct code review comments than the static LLM-based baseline, and also substantially surpasses SAST tools. Moreover, AgenticSCR generates more correct comments in four out of five vulnerability types, consistently and significantly outperforming all other baselines. These findings highlight the importance of Agentic Secure Code Review, paving the way towards an emerging research area of immature vulnerability detection.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19138
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
Charoenwet, Wachiraphan
Tantithamthavorn, Kla
Thongtanunam, Patanamon
Lin, Hong Yi
Jeong, Minwoo
Wu, Ming
Cryptography and Security
Artificial Intelligence
Machine Learning
Software Engineering
Secure code review is critical at the pre-commit stage, where vulnerabilities must be caught early under tight latency and limited-context constraints. Existing SAST-based checks are noisy and often miss immature, context-dependent vulnerabilities, while standalone Large Language Models (LLMs) are constrained by context windows and lack explicit tool use. Agentic AI, which combine LLMs with autonomous decision-making, tool invocation, and code navigation, offer a promising alternative, but their effectiveness for pre-commit secure code review is not yet well understood. In this work, we introduce AgenticSCR, an agentic AI for secure code review for detecting immature vulnerabilities during the pre-commit stage, augmented by security-focused semantic memories. Using our own curated benchmark of immature vulnerabilities, tailored to the pre-commit secure code review, we empirically evaluate how accurate is our AgenticSCR for localizing, detecting, and explaining immature vulnerabilities. Our results show that AgenticSCR achieves at least 153% relatively higher percentage of correct code review comments than the static LLM-based baseline, and also substantially surpasses SAST tools. Moreover, AgenticSCR generates more correct comments in four out of five vulnerability types, consistently and significantly outperforming all other baselines. These findings highlight the importance of Agentic Secure Code Review, paving the way towards an emerging research area of immature vulnerability detection.
title AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
topic Cryptography and Security
Artificial Intelligence
Machine Learning
Software Engineering
url https://arxiv.org/abs/2601.19138