Metraipolis › archive › dc_19212cd38709

CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection — arXiv:2608.03134

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03134
License (as archived)
CC0-1.0
Archived
2026-10-31T12:34:23.534Z
SHA-256 of the archived text
b3650d1328689e8f94a8d33fec3799f76aa846302b1ed57f1108bc862832bc90
Stable URL of this page
https://metraipolis.com/documento/dc_19212cd38709

How to cite

CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection — arXiv:2608.03134 — arXiv (en), https://arxiv.org/abs/2608.03134 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19212cd38709 (Metraipolis archive dc_19212cd38709, sha256 b3650d1328689e8f94a8d33fec3799f76aa846302b1ed57f1108bc862832bc90)
BibTeX
@misc{dc19212cd38709,
  title = {CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection — arXiv:2608.03134},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03134},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19212cd38709; sha256 b3650d1328689e8f94a8d33fec3799f76aa846302b1ed57f1108bc862832bc90},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03134. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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, demonstrating the effectiveness of causal knowledge graph-guided reasoning for automated vulnerability detection.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.03134 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:21:50.553Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).