# Towards Agentic Honeynet Configuration

arXiv: https://arxiv.org/abs/2603.14122 · HTML: https://mlsanity.com/paper/2603.14122/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [LLM in the Shell: Generative Honeypots](https://mlsanity.com/paper/2309.00155/) (2023)
- [LLM Honeypot: Leveraging Large Language Models as Advanced Interactive Honeypot Systems](https://mlsanity.com/paper/2409.08234/) (2024)
- [Adaptive Honeypot Engagement through Reinforcement Learning of Semi-Markov Decision Processes](https://mlsanity.com/paper/1906.12182/) (2019)
- [HoneyGPT: Breaking the Trilemma in Terminal Honeypots with Large Language Model](https://mlsanity.com/paper/2406.01882/) (2024)
- [LLMPot: Dynamically Configured LLM-based Honeypot for Industrial Protocol and Physical Process Emulation](https://mlsanity.com/paper/2405.05999/) (2024)
- [HoneyIoT: Adaptive High-Interaction Honeypot for IoT Devices Through Reinforcement Learning](https://mlsanity.com/paper/2305.06430/) (2023)

## Abstract (arXiv)

Honeypots are deception systems that emulate vulnerable services to collect threat intelligence. While deploying many honeypots increases the opportunity to observe attacker behaviour, in practise network and computational resources limit the number of honeypots that can be exposed. Hence, practitioners must select the assets to deploy, a decision that is typically made statically despite attackers' tactics evolving over time. This work investigates an AI-driven agentic architecture that autonomously manages honeypot exposure in response to ongoing attacks. The proposed agent analyses Intrusion Detection System (IDS) alerts and network state to infer the progression of the attack, identify compromised assets, and predict likely attacker targets. Based on this assessment, the agent dynamically reconfigures the system to maintain attacker engagement while minimizing unnecessary exposure. The approach is evaluated in a simulated environment where attackers execute Proof-of-Concept exploits for known CVEs. Preliminary results indicate that the agent can effectively infer the intent of the attacker and improve the efficiency of exposure under resource constraints