Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation

Computer Science > Cryptography and Security [Submitted on 24 Apr 2026] Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation Biagio Andreucci, Arcangelo Castiglione The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service (DoS) risks, Automatic Exploit Generation (AEG) systems suffer from semantic blindness, and Large Language Model (LLM) agents face safety alignment filters and "Live Fire" execution hazards. We introduce Automation-Exploit, a fully autonomous Multi-Agent System (MAS) framework designed for adaptive offensive security in complex black-box scenarios. It bridges the abstraction gap between reconnaissance and exploitation by autonomously exfiltrating executables and contextual intelligence across multiple protocols, using this data to fuel both logical and binary attack chains. The framework introduces an adaptive safety architecture to mitigate DoS risks. While it natively resolves logical and web-based vulnerabilities, it employs a conditional isomorphic validation for high-risk memory-corruption flaws: if the target binary is successfully exfiltrated, it dynamically instantiates a cross-platform digital twin. By enforcing strict state synchronization, including libc alignment and runtime file descriptor hooking, potentially destructive payloads are iteratively debugged in an isolated replica. This enables a highly risk-mitigated "one-shot" execution on the physical target. Empirical evaluations across eight scenarios, including undocumented zero-day environments to rule out LLM data contamination, validate the framework's architectural resilience, demonstrating its ability to prevent "live fire" crashes and execute risk-mitigated compromises on actual targets. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2604.22427 [cs.CR]   (or arXiv:2604.22427v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.22427 Focus to learn more Submission history From: Biagio Andreucci [view email] [v1] Fri, 24 Apr 2026 10:38:40 UTC (21,000 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)