# Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting

arXiv: https://arxiv.org/abs/2609.15523 · HTML: https://mlsanity.com/paper/2609.15523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 9 of 9)

- [Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks](https://mlsanity.com/paper/2501.16466/) (2025)
- [CAI: An Open, Bug Bounty-Ready Cybersecurity AI](https://mlsanity.com/paper/2504.06017/) (2025)
- [MCP-Solver: Integrating Language Models with Constraint Programming Systems](https://mlsanity.com/paper/2501.00539/) (2024)
- [On the Surprising Efficacy of LLMs for Penetration-Testing](https://mlsanity.com/paper/2507.00829/) (2025)
- [ATAG: AI-Agent Application Threat Assessment with Attack Graphs](https://mlsanity.com/paper/2506.02859/) (2025)
- [CAI Fluency: A Framework for Cybersecurity AI Fluency](https://mlsanity.com/paper/2508.13588/) (2025)
- [A Survey of MulVAL Extensions and Their Attack Scenarios Coverage](https://mlsanity.com/paper/2208.05750/) (2022)
- [Graph models for Cybersecurity -- A Survey](https://mlsanity.com/paper/2311.10050/) (2023)
- [EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming](https://mlsanity.com/paper/2608.01763/) (2026)

## Abstract (arXiv)

Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic frameworks such as MulVAL to contemporary security workflows or agentic pipelines, however, requires translating scanner evidence to initial facts, and creating domain-specific rules. We present a semi-automated pipeline that addresses this interoperability problem and depict its feasibility in a web-security case study. Our pipeline parses findings from Trivy, Semgrep, and Nmap into MulVAL predicates and uses an LLM-assisted process to construct domain-specific Datalog rules linking scanner-detectable evidence to attack techniques. MulVAL/XSB then performs symbolic inference to generate structured attack paths. We evaluate the attack-graph construction infrastructure on 54 web Capture-the-Flag tasks from CyBench within an agentic pipeline (Hybrid Reasoner); we do not evaluate the performance of the downstream agent. Every task produced at least one goal-reaching graph, and we achieve mean ground-truth vulnerability coverage of 53.7%, with 51.9% achieving full coverage; mean noise-path rate was 83.9%. With median end-to-end time of 24.9 s (MulVAL reasoning: 2.7 s) the pipeline is feasible and runtime-practical for agentic workflows, but predicate coverage, rule coverage, and path precision remain limiting factors. Next steps include semantic rule validation and agent-level comparison for graph-guided pentesting.