# CVE2AP: Automated Generation of PDDL-Encoded Attack Paths via Large Language Models

arXiv: https://arxiv.org/abs/2610.03383 · HTML: https://mlsanity.com/paper/2610.03383/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 7 of 7)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [On the Limit of Language Models as Planning Formalizers](https://mlsanity.com/paper/2412.09879/) (2024)
- [Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts](https://mlsanity.com/paper/2409.15915/) (2024)
- [Generating consistent PDDL domains with Large Language Models](https://mlsanity.com/paper/2404.07751/) (2024)
- [Attack Planning in the Real World](https://mlsanity.com/paper/1306.4044/) (2013)

## Abstract (arXiv)

Attack Path (AP) modeling is fundamental to cybersecurity analysis, where the Planning Domain Definition Language (PDDL) has been widely adopted to encode APs into formal and machine-verifiable representations for automated reasoning about vulnerability exploitation, attack progression, and their potential impacts. However, existing AP modeling approaches largely rely on expert-driven manual construction, limiting their scalability and ability to keep pace with rapidly evolving cyber threats. Large language models (LLMs) are promising candidates, as their extensive pre-trained knowledge and reasoning capabilities enable them to interpret and transform threat intelligence into formal representations. In this paper, we propose CVE2AP, an LLM-based approach for automatically generating PDDL-encoded attack paths from natural language CVE (Common Vulnerability Exposure) descriptions. CVE2AP leverages structured prompting and incorporates an error-feedback mechanism that iteratively refines the generated paths using planner-reported syntactic and solvability errors. We conduct a systematic empirical evaluation across multiple LLMs and generation configurations, assessing generation quality across syntactic, solvability and semantic dimensions, together with token consumption and generation time. The results demonstrate that CVE2AP effectively generates high-quality PDDL-encoded attack paths, achieving up to 86.9% syntax correctness, 78.6% solvability, and 93.1% semantic correctness under LLM-as-expert evaluation, while textttGPT-5.5 offers the best quality-cost trade-off and error feedback yields the most consistent quality improvement.