Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied. Meanwhile, recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have improved LLM reasoning, but their integration into cybersecurity remains elusive due to the absence of suitable benchmark environments and interaction datasets.
arXiv:2608. 04317v1 Announce Type: cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied.
By Ryozo Masukawa, Ian Bryant, Armita Kazeminajafabadi, Sanggeon Yun, Hyunwoo Oh, SungHeon Jeong, Nathaniel D. Bastian, Mahdi Imani, Mohsen Imani
arXiv:2610.00590v1 Announce Type: cross
Abstract: An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability...
By Harshith Doppalapudi, Nathaniel D. Bastian, Ankit Shah
arXiv:2610.00557v1 Announce Type: cross
Abstract: Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement le...
By Ayan Javeed Shaikh, Arunesh Sinha, Nathaniel D. Bastian, Ankit Shah
arXiv:2606. 18223v1 Announce Type: cross Abstract: With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained via Reinforcement Learning (RL).
By Ankita Samaddar, Sandeep Neema, Daniel Balasubramanian, Xenofon Koutsoukos
arXiv:2602. 04809v3 Announce Type: replace Abstract: Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning.
By Elizabeth Bates, Chris Hicks, Vasilios Mavroudis
arXiv:2606. 13079v1 Announce Type: cross Abstract: Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines that frontier AI systems must not cross.
By Jiaqi Luo, Jiarun Dai, Zhile Chen, Jia Xu, Weibing Wang, Yawen Duan, Brian Tse, Geng Hong, Xudong Pan, Yuan Zhang, Min Yang
arXiv:2606. 01991v1 Announce Type: new Abstract: As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the risk of power-seeking.
By Lichao Wang, Zhaoxing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai
arXiv:2604. 09523v2 Announce Type: replace Abstract: Training reinforcement-learning agents for cyber defense requires an environment that reflects the operational setting: noisy, partial observations, several defenders coordinating across a network, and an adaptive adversary realized through self-play.
By Igor Jankowski
arXiv:2608.23181v1 Announce Type: cross
Abstract: As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention,...
By Jian Yang, Haau-Sing Li, Shawn Guo, Zixi Zhao, Yibo Tan, Jiajun Wu, Aishan Liu, Xianglong Liu, Tianyu Zheng, Bryan Dai, Chengran Yang
arXiv:2608.29596v1 Announce Type: new
Abstract: Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on c...
By Sanket Badhe, Deep Shah, Priyanka Tiwari, Nehal Kathrotia
The study evaluates autonomous agents that respond to network intrusions within a cyber range designed for human operator training. Using an emulated network with variable topology, red‑team attacks, and simulated users, the agents aim to block unauthorized access while minimizing defensive costs. Experiments compare heuristic policies with reinforcement‑learning‑derived policies, finding that the latter generally defend more efficiently, though performance varies with adversary strategy and user simulation.
By Jakob Nyberg, Teodor Sommestad, Andrei Buhaiu, Joakim Loxdal, Pontus Johnson, Mathias Ekstedt