一句话：提出 CLEAR 多智能体框架，结合漏洞因果知识图谱，通过因果上下文推理提升源代码漏洞检测准确率。
现代安全漏洞常源于执行流、控制条件与程序状态之间复杂的因果依赖，而现有基于大语言模型和多智能体的漏洞检测方法多关注良性与脆弱函数间的表面相似性，难以捕捉这些因果依赖。为此，作者提出 CLEAR，一种集成因果知识图谱的多智能体漏洞检测框架。CLEAR 系统性地构建漏洞因果知识图谱（VCKG），建模入口点、前置条件、根因与修复意图之间的因果链；并利用 Collector、Claim、Critic、Judge 四个专门智能体，通过检索到的因果上下文协作验证漏洞假设。在 C/C++ 和 Java 漏洞基准上的实验表明，CLEAR 相对最先进方法将 Pair-Correct（P-C）性能分别提升 130.7% 和 71.56%，验证了因果知识图谱引导推理在自动漏洞检测中的有效性。
Detecting source code vulnerabilities is increasingly difficult as modern security flaws are rooted in complex causal dependencies between execution flows, control conditions, and program states. Despite recent advances in Large Language Models (LLMs) and multi-agent frameworks, existing approaches primarily address superficial similarities between benign and vulnerable functions while failing to capture the complex causal dependencies inherent in security flaws. To address these limitations, we propose Causal Context-based Agentic Reasoning (CLEAR), a novel multi-agent vulnerability detection framework integrated with a causal knowledge graph. CLEAR systematically constructs a Vulnerability Causal Knowledge Graph (VCKG) that models the causal chains between entrypoints, preconditions, root causes, and fix intents across vulnerability instances. Leveraging this structured knowledge, four specialized agents including the Collector, Claim, Critic, and Judge collaboratively verify vulnerability hypotheses through retrieved causal contexts. Experimental results on C/C++ and Java vulnerability benchmarks demonstrate that CLEAR improves Pair-Correct (P-C) performance by 130.7% and 71.56% over state-of-the-art approaches, respectively, demonstrating the effectiveness of causal knowledge graph–guided reasoning for automated vulnerability detection.
@inproceedings{paperbot12619,
title = {CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection},
author = {Sungju Yun and Sijune Hwang and Yeonjoon Lee and Kyungtae Kang and Sungbin Park},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3837523}
}