# AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises

arXiv: https://arxiv.org/abs/2601.22720 · HTML: https://mlsanity.com/paper/2601.22720/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 81 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 15 of 15)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [LLM Agents can Autonomously Exploit One-day Vulnerabilities](https://mlsanity.com/paper/2404.08144/) (2024)
- [AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks](https://mlsanity.com/paper/2403.01038/) (2024)
- [Teams of LLM Agents can Exploit Zero-Day Vulnerabilities](https://mlsanity.com/paper/2406.01637/) (2024)
- [Autonomous Penetration Testing using Reinforcement Learning](https://mlsanity.com/paper/1905.05965/) (2019)
- [Frontier AI's Impact on the Cybersecurity Landscape](https://mlsanity.com/paper/2504.05408/) (2025)
- [Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks](https://mlsanity.com/paper/2502.04227/) (2025)
- [AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?](https://mlsanity.com/paper/2411.01236/) (2024)
- [The Concept of Cyber Defence Exercises (CDX): Planning, Execution, Evaluation](https://mlsanity.com/paper/1906.03184/) (2019)
- [AiCEF: An AI-assisted Cyber Exercise Content Generation Framework Using Named Entity Recognition](https://mlsanity.com/paper/2211.10806/) (2022)
- [Vital: Vulnerability-Oriented Symbolic Execution via Type-Unsafe Pointer-Guided Monte Carlo Tree Search](https://mlsanity.com/paper/2408.08772/) (2024)

## Built on by (most cited first, 1 of 1)

- [Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing](https://mlsanity.com/paper/2606.25332/) (2026)

## Abstract (arXiv)

Creating attack paths for cyber defence exercises requires substantial expert effort. Existing automation requires vulnerability graphs or exploit sets curated in advance, limiting where it can be applied. We present AEGIS, a system that generates attack paths using LLMs, white-box access, and Monte Carlo Tree Search over real exploit execution. LLM-based search discovers exploits dynamically without pre-existing vulnerability graphs, while white-box access enables validating exploits in isolation before committing to attack paths. Evaluation at CIDeX 2025, a large-scale exercise spanning 46 IT hosts, showed that AEGIS-generated paths are comparable to human-authored scenarios across four dimensions of training experience (perceived learning, engagement, believability, challenge). Results were measured with a validated questionnaire extensible to general simulation-based training. By automating exploit chain discovery and validation, AEGIS reduces scenario development from months to days, shifting expert effort from technical validation to scenario design.