Large language models (LLMs) are increasingly studied for software vulnerability detection, but the benefits of recent reasoning-enabled (“thinking”) modes remain unclear. At the same time, agentic LLM designs aim to enhance analysis through structured collaboration, while practical software security workflows require...
Hua-Beng Tan, Ratnadira Widyasari, Merve Astekin et al.· Proceedings of the 41st IEEE...· 0 citations
Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are created at evaluation time, so no content exists in advance to leak, and its difficulty i...
Wei Minn, Zhensu Sun, L. K. Shar et al.· 0 citations
Large language models (LLMs) are increasingly used in software engineering, including agentic systems that coordinate multiple agents, but impose higher computational and environmental costs. In this paper, we present a comprehensive empirical study of agentic LLM systems across five software engineering tasks: code ge...
Merve Astekin, Yan Naing Tun, Arda Goknil et al.· 0 citations
Vulnerability-detection benchmarks score the verdict an agent reaches, not the evidence it gathered. A model that recalls a CVE from pretraining therefore scores the same as one that traced the data flow. We study a task where this difference matters, deciding whether a commit introduces a vulnerability. Instead of sco...
Yi-Kun Li, Jin-Feng Jiang, Yuheng Yieh et al.· 0 citations
Evaluations across agent systems, benchmarks, and backbone LLMs under 65 fault configurations show that all systems degrade under fault injection, suggesting that robustness depends on system implementation rather than model capability.
Gou Tan, Zhensu Sun, Jie-Ke Shi et al.· Proceedings of the 41st IEEE...· 6 citations
VulAgentRL is proposed, an agentic RL framework for interprocedural vulnerability detection built on a Code Property Graph (CPG), which outperforms state-of-the-art baselines, including frontier models, on the strict pair-wise-correct metric while issuing fewer tool calls, and its advantage persists on an out-of-distri...
Yi-Kun Li, Ting Zhang, Jia-Kun Liu et al.· arXiv.org· 2 citations
Experiments on real-world vulnerabilities show that CoSA consistently outperforms function-level and pure-LLM baselines, suggesting that explicit, metric-oriented repository context retrieval is crucial for practical and reliable automated severity assessment.
Jin-Feng Jiang, Yi-Kun Li, Cheng-Ran Yang et al.· 0 citations
This survey presents a comprehensive review of research studies closely related to UAV anomalies published between 2015 and 2025, covering 111 papers from academic and industrial sources, and introduces a unified five-pillar taxonomy that organizes existing work across the full anomaly management lifecycle.
Ivan Tan, Christopher M. Poskitt, Ling-Xiao Jiang et al.· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
