One Pipeline Does Not Fit All: TAILOR, a Type- and State-Aware Framework for CVE Reproduction

arXiv:2609.37006 · cs.CR · Submitted 2026-09-29 · Read on arXiv

cs.CR

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Verification — 35× in this paper · explained in 2 episodes
• Verifier — 21× in this paper · explained in 2 episodes
• Core — 15× in this paper · explained in 2 episodes
• Actor — 13× in this paper · explained in 3 episodes
• Trace — 9× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• Multi-Agent Framework — 4× in this paper · explained in 3 episodes
• Multi-Agent System — 3× in this paper · explained in 6 episodes
• Provenance — 3× in this paper · explained in 4 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• Reproduction Success Rate — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Agentic LLM Systems — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Formal Verification — 1× in this paper · explained in 2 episodes
• IEEE Symposium on Security and Privacy — 1× in this paper
• International Conference on Learning Representations — 1× in this paper
• International Conference on Mining Software Repositories — 1× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Network and Distributed System Security Symposium — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software
• From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
• Frontier AI's Impact on the Cybersecurity Landscape
• SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned
• LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
• Automated Vulnerability Validation and Verification: A Large Language Model Approach
• Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction
• PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
• Program Analysis Guided LLM Agent for Proof-of-Concept Generation
• FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents
• A Dual-Loop Agent Framework for Automated Vulnerability Reproduction
• AXE: Grey-Box Exploitability Confirmation for Localized Vulnerability Reports
• LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
• MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs