EUVIMEDEUVIMED entdecken
Crossref

In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach

Yiran Gao, Kim Hammar, Tao Li

Proceedings of the AAAI Symposium Series · 23.06.2026 · 9 (1) · 246-254

DOI: 10.1609/aaaiss.v9i1.42938 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 23.06.2026. Verfasst von Yiran Gao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies through extensive simulation of the incident. While this approach can be effective, it requires handcrafted modeling of the simulator and suppresses useful semantics from raw system logs and alerts. To address these limitations, we propose to leverage large language models' (LLMs) pre-trained security knowledge and in-context learning to create an end-to-end agentic solution for incident response planning. Specifically, our agent integrates four functionalities, perception, reasoning, planning, and action, into one lightweight LLM (14b model). Through fine-tuning and chain-of-thought reasoning, our LLM agent is capable of processing system logs and inferring the underlying network state (perception), updating its conjecture of attack models (reasoning), simulating consequences under different response strategies (planning), and generating an effective response (action). By comparing LLM-simulated outcomes with actual observations, the LLM agent repeatedly refines its attack conjecture and corresponding response, thereby demonstrating in-context adaptation. Our agentic approach is free of modeling and can run on commodity hardware. When evaluated on incident logs reported in the literature, our agent achieves recovery up to 23% faster than those of frontier LLMs.

Zitieren

APA

Gao, Y., Hammar, K., & Li, T. (2026). In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach. Proceedings of the AAAI Symposium Series, 9(1), 246-254. https://doi.org/10.1609/aaaiss.v9i1.42938

Vancouver

Gao Y, Hammar K, Li T. In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach. Proceedings of the AAAI Symposium Series. 2026;9(1):246-254. doi:10.1609/aaaiss.v9i1.42938

BibTeX
@article{Gao2026,
  author = {Gao, Yiran and Hammar, Kim and Li, Tao},
  title = {In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach},
  journal = {Proceedings of the AAAI Symposium Series},
  year = {2026},
  volume = {9},
  number = {1},
  pages = {246--254},
  doi = {10.1609/aaaiss.v9i1.42938}
}
Kostenlos starten →