When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

Computer Science > Cryptography and Security [Submitted on 9 May 2026] When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions Minfeng Qi, Tianqing Zhu, Zijie Xu, Congcong Zhu, Qin Wang, Wanlei Zhou Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and validation into one context, which increases the risk of context drift and error propagation. Existing LLM-based multi-agent systems support general collaboration, but they do not explicitly model the role boundaries, artifact provenance, and cost constraints that characterize multi-stage intrusion workflows. This paper presents CAESAR, a coordinated multi-agent framework for controlled analysis of LLM-agent behavior in intrusion-style tasks. CAESAR decomposes the workflow into five typed roles and coordinates them through a bounded round protocol with a persistent knowledge base, a per-round workspace, validator-gated knowledge promotion, and capability-token write isolation. We evaluate CAESAR on 25 CTF tasks across five categories and four LLM backends. Compared with a single-agent baseline under matched budgets and tool access, CAESAR improves task success and reduces performance variance, with larger gains on tasks requiring multi-step exploit composition. A secondary simulated interactional-security study suggests that the role structure can transfer beyond code-native surfaces. The results indicate that role transitions, artifact provenance, and knowledge-promotion events provide useful structural signals for monitoring coordinated LLM-agent behavior beyond individual prompt and output inspection. The dataset, implementation, and evaluation logs are released at this https URL. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2605.08763 [cs.CR]   (or arXiv:2605.08763v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.08763 Focus to learn more Submission history From: Minfeng Qi [view email] [v1] Sat, 9 May 2026 07:47:42 UTC (1,654 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 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?)