MetaVul is a self‑improving framework that discovers and refines harnesses—code scaffolding around large language model agents—for vulnerability detection. Starting from a seed reasoning scaffold, it iteratively optimizes harnesses using feedback from paired vulnerable and patched functions, producing Pareto‑optimal designs that can be reused across different models. Experiments show that optimized harnesses can boost pairwise vulnerability detection by up to 25.8 percentage points and transfer effectively between models without further tuning.
arXiv:2607. 12058v1 Announce Type: cross Abstract: Given a vulnerability-fixing commit, trigger localization asks which specific statement turns the vulnerable program state into a concrete unsafe operation.
arXiv:2609.22792v1 Announce Type: cross Abstract: LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model...
The paper surveys 87 influential studies on machine‑learning‑based automated vulnerability detection (ML4AVD), categorizing them by problem formulation, input and detection granularity, target languages, evaluation metrics, datasets, and detection approaches. It identifies twelve self‑reinforcing pain points—such as overreliance on binary classification of C/C++ function‑level vulnerabilities, limited language coverage, and intertwined datasets, baselines, and metrics—that trap the field in a narrow, artificial problem space. The authors propose concrete recommendations to break these feedback loops and evaluate a recent high‑profile effort, AIxCC, against these guidelines, reflecting on ML4AVD’s relevance amid the rise of agentic AI.
arXiv:2607. 11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable.
PatchBench introduces a benchmark to evaluate AI agents on realistic vulnerability patching tasks, addressing two key threats to validity: patch memorization and surface-level fixes that merely suppress crashes. The study finds that 25% of agent patches resemble historical developer patches, and that PoC-only validation inflates success rates by 1.83× on average. PatchBench mitigates these issues by selecting vulnerabilities whose true fixes lie outside the crash stack, migrating historical vulnerabilities into new contexts, and employing rigorous validation for security and semantic correctness.
arXiv:2608. 06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software.
arXiv:2606. 03453v1 Announce Type: cross Abstract: Vulnerability disclosure volumes now far exceed organizational assessment capacity, yet three adjacent research communities (proof-of-concept generation, vulnerability prioritization, and detection rule engineering) operate largely in isolation.
arXiv:2604.10800v2 Announce Type: replace-cross Abstract: Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verif...
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools.
arXiv:2609.06229v1 Announce Type: cross Abstract: Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical...
arXiv:2607. 26656v1 Announce Type: cross Abstract: Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real CVEs, we find that 71.
arXiv:2606. 19149v1 Announce Type: cross Abstract: Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approaches such as fuzzing require substantial infrastructure and often target narrow classes of bugs.