[1] SCHWARTZ J, KURNIAWATI H. Autonomous penetration testing using reinforcement learning[EB/OL]. [2026-09-10]. https://arxiv.org/abs/1905.05965.
[2] LIU J, ZHANG Y, ZHOU S, et al. Autonomous penetration testing using reinforcement learning: A review and perspectives[J]. Expert Systems with Applications, 2026, 300: 130219. DOI:10.1016/j.eswa.2025.130219.
[3] ZHOU S, LIU J, LU Y, et al. SCRIPT: A scalable continual reinforcement learning framework for autonomous penetration testing[J]. Expert Systems with Applications, 2025, 285: 127827. DOI:10.1016/j.eswa.2025.127827.
[4] HU Z, BEURAN R, TAN Y. Automated penetration testing using deep reinforcement learning[C]//2020 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW). Washington D. C., USA: IEEE Press, 2020: 2-10. DOI:10.1109/EuroSPW51379.2020.00010.
[5] ZHOU S, LIU J, HOU D, et al. Autonomous penetration testing based on improved Deep Q-Network[J]. Applied Sciences, 2021, 11(19): 8823. DOI:10.3390/app11198823.
[6] GHANEM M C, CHEN T M. Reinforcement learning for intelligent penetration testing[C]//2018 Second World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4). Washington D. C., USA: IEEE Press, 2018: 185-192. DOI:10.1109/WorldS4.2018.8611595.
[7] LÓPEZ-MONTERO D, ÁLVAREZ-ALDANA J L, MORALES-MARTÍNEZ A, et al. Reinforcement learning for automated cybersecurity penetration testing[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2507.02969.
[8] 周仕承, 刘京菊, 钟晓峰, 等. 基于深度强化学习的智能化渗透测试路径发现[J]. 计算机科学, 2021, 48(7): 40-46. DOI:10.11896/jsjkx.210400057.
ZHOU S C, LIU J J, ZHONG X F, et al. Intelligent penetration testing path discovery based on deep reinforcement learning[J]. Computer Science, 2021, 48(7): 40-46. DOI:10.11896/jsjkx.210400057. (in Chinese).
[9] LAN J H, LV Z, LI J C, et al. A3C reinforcement learning-based automated penetration testing for industrial control systems[C]//Third International Conference on Power Electronics and Artificial Intelligence (PEAI 2026). Bellingham, USA: SPIE, 2026: 141361D. DOI:10.1117/12.3111342.
[10] PATKI A, JADHAV P, TAYADE G, et al. An AI-powered tool for automated web application penetration testing using PPO[J]. International Journal of Electrical, Electronics and Computer Systems, 2026, 15(1S): 212-216. DOI:10.65521/ijeecs.v15i1S.3056.
[11] KONG H, HU D, GE J, et al. Pentest-R1: Towards autonomous penetration testing reasoning optimized via two-stage reinforcement learning[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2508.07382.
[12] YANG Y, CHEN L, LIU S, et al. Behaviour-diverse automatic penetration testing: A coverage-based deep reinforcement learning approach[J]. Frontiers of Computer Science, 2025, 19(3): 193309. DOI:10.1007/s11704-024-3380-1.
[13] PRATAMA D, SURYANTO N, ADIPUTRA A A, et al. CIPHER: Cybersecurity intelligent penetration-testing helper for ethical researcher[J]. Sensors, 2024, 24(21): 6878. DOI:10.3390/s24216878.
[14] BESSA R, CLARO R, TRINDADE J, et al. Towards automated pentesting with large language models[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2604.11772.
[15] ZHUO T Y, WANG D, DING H, et al. Cyber-Zero: Training cybersecurity agents without runtime[C/OL]//International Conference on Learning Representations (ICLR 2026). 2026[2026-10-14]. https://openreview.net/forum?id=D9kdB63vUJ.
[16] ZHUO T Y, WANG D, DING H, et al. Training language model agents to find vulnerabilities with CTF-Dojo[C/OL]//Proceedings of the 43rd International Conference on Machine Learning. Proceedings of Machine Learning Research, 2026, 306: 168265-168284[2026-10-14]. https://proceedings.mlr.press/v306/zhuo26c.html.
[17] DENG G, LIU Y, MAYORAL-VILCHES V, et al. PentestGPT: Evaluating and harnessing large language models for automated penetration testing[C]//33rd USENIX Security Symposium (USENIX Security 24). Berkeley, USA: USENIX Association, 2024: 847-864.
[18] HUANG J J, ZHU Q Y. PenHeal: A two-stage LLM framework for automated pentesting and optimal remediation[C]//Proceedings of the Workshop on Autonomous Cybersecurity. New York, USA: ACM, 2024: 11-22. DOI:10.1145/3689933.3690831.
[19] MUZSAI L, IMOLAI D, LUKÁCS A. HackSynth: LLM agent and evaluation framework for autonomous penetration testing[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2412.01778.
[20] WU L, ZHONG X, LIU J, et al. PTGroup: An automated penetration testing framework using LLMs and multiple prompt chains[C]//Advanced Intelligent Computing Technology and Applications: 20th International Conference, ICIC 2024, Tianjin, China, August 5-8, 2024, Proceedings, Part IX. Lecture Notes in Computer Science, vol. 14870. Singapore: Springer, 2024: 220-232. DOI:10.1007/978-981-97-5606-3_19.
[21] XU J, STOKES J W, MCDONALD G, et al. AutoAttacker: A large language model guided system to implement automatic cyber-attacks[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2403.01038.
[22] ALSHEHRI I, ALSHEHRI A, ALMALKI I, et al. BreachSeek: A multi-agent automated penetration tester[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2409.03789.
[23] BIANOU S G, BATOGNA R G. PENTEST-AI, an LLM-powered multi-agents framework for penetration testing automation leveraging MITRE ATT&CK[C]//2024 IEEE International Conference on Cyber Security and Resilience (CSR). Washington D. C., USA: IEEE Press, 2024: 763-770. DOI:10.1109/CSR61664.2024.10679480.
[24] SHEN X M, WANG L Z, LI Z Y, et al. PentestAgent: Incorporating LLM agents to automated penetration testing[C]//Proceedings of the 20th ACM Asia Conference on Computer and Communications Security. New York, USA: ACM, 2025: 375-391. DOI:10.1145/3708821.3733882.
[25] WU B, CHEN G, CHEN K, et al. AutoPT: How far are we from the fully automated Web penetration testing?[J]. IEEE Transactions on Information Forensics and Security, 2025, 20: 9657-9672. DOI:10.1109/TIFS.2025.3601343.
[26] KONG H, HU D, GE J, et al. VulnBot: Autonomous penetration testing for a multi-agent collaborative framework[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2501.13411.
[27] ZHAI J, ZHOU X, MIAO H, et al. PentestMCP: LLM and MCP based multi-agent framework for automated penetration testing[EB/OL]. [2026-10-13]. DOI:10.21203/rs.3.rs-7582841/v1.
[28] 江颉, 蔡辰旭, 李明达, 等. 基于大语言模型和RAG的自动化渗透测试框架研究[J]. 电信科学, 2025, 41(9): 119-132. DOI:10.11959/j.issn.1000-0801.2025159.
JIANG J, CAI C X, LI M D, et al. Research on an automated penetration testing framework based on LLM and RAG[J]. Telecommunications Science, 2025, 41(9): 119-132. DOI:10.11959/j.issn.1000-0801.2025159. (in Chinese).
[29] GINIGE Y, NIROSHAN A, JAIN S, et al. AutoPentester: An LLM agent-based framework for automated pentesting[C]//2025 IEEE 24th International Conference on Trust, Security and Privacy in Computing and Communicatio ns (TrustCom). Washington D. C., USA: IEEE Press, 2025: 163-174. DOI:10.1109/Trustcom66490.2025.00026.
[30] HENKE J. AutoPentest: Enhancing vulnerability management with autonomous LLM agents[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2505.10321.
[31] NAKATANI S. RapidPen: Fully automated IP-to-Shell penetration testing with LLM-based agents[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2502.16730.
[32] DAVID I, GERVAIS A. Multi-agent penetration testing AI for the Web[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2508.20816.
[33] NIEPONICE T, VALEROS V, GARCIA S. ARACNE: An LLM-based autonomous Shell pentesting agent[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2502.18528.
[34] MAI W, HONG G, LIU Q, et al. Shell or nothing: Real-world benchmarks and memory-activated agents for automated penetration testing[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2509.
[35] LUONG P D, BAO L T G, TAM N V, et al. xOffense: An autonomous multi-agent framework for penetration testing with domain-adapted large language models[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2509.13021.
[36] WANG L, SHI X, LI Z, et al. Automated penetration testing with LLM agents and classical planning[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2512.11143.
[37] DAI H, LI Y, YAN J, et al. RefPentester: A knowledge-informed self-reflective penetration testing framework based on large language models[C]//2025 22nd Annual International Conference on Privacy, Security, and Trust (PST). Washington D. C., USA: IEEE Press, 2025: 1-8. DOI:10.1109/PST65910.2025.11268838.
[38] MAYORAL-VILCHES V, NAVARRETE-LOZANO L J, SANZ-GÓMEZ M, et al. CAI: An open, bug bounty-ready cybersecurity AI[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2504.06017.
[39] ABRAMOVICH T, UDESHI M, SHAO M, et al. EnIGMA: Interactive tools substantially assist LM agents in finding security vulnerabilities[C/OL]//Proceedings of the 42nd International Conference on Machine Learning. Proceedings of Machine Learning Research, 2025, 267: 246-355[2026-10-14]. https://proceedings.mlr.press/v267/abramovich25a.html.
[40] NAKANO K, FAYYAZI R, YANG S J, et al. Guided reasoning in LLM-driven penetration testing using structured attack trees[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2509.07939.
[41] CALDWELL S, HARLEY M, KOUREMETIS M, et al. PentestJudge: Judging agent behavior against operational requirements[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2508.02921.
[42] YANG R, CHENG M, DENG G, et al. PentestEval: Benchmarking LLM-based penetration testing with modular and stage-level design[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2512.14233.
[43] GIOACCHINI L, DELSANTO A, DRAGO I, et al. AutoPenBench: A vulnerability testing benchmark for generative agents[C]//Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. Stroudsburg, USA: Association for Computational Linguistics, 2025: 1615-1624. DOI:10.18653/v1/2025.emnlp-industry.114.
[44] SHEN X, CHENG W, CHEN Y, et al. AEAS: Actionable exploit assessment system[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2509.17832.
[45] ISOZAKI I, SHRESTHA M, CONSOLE R, et al. Towards automated penetration testing: Introducing LLM benchmark, analysis, and improvements[C]//Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization. New York, USA: ACM, 2025: 404-419. DOI:10.1145/3708319.3733804.
[46] ZHU Y, KELLERMANN A, BOWMAN D, et al. CVE-Bench: A benchmark for AI agents’ ability to exploit real-world Web application vulnerabilities[C/OL]//Proceedings of the 42nd International Conference on Machine Learning. Proceedings of Machine Learning Research, 2025, 267: 79850-79867[2026-10-14]. https://proceedings.mlr.press/v267/zhu25i.html.
[47] JASWAL A S, BAGHEL A. AWE: Adaptive agents for dynamic Web penetration testing[C/OL]//Proceedings of the 2026 Workshop on LLM Assisted Security and Trust Exploration (LAST-X 2026). Reston, USA: The Internet Society, 2026[2026-10-14]. DOI:10.14722/last-x.2026.23037.
[48] VANGELI M, BRYNIELSSON J, COHEN M, et al. Context relay for long-running penetration-testing agents[C/OL]//Proceedings of the 2026 Workshop on LLM Assisted Security and Trust Exploration (LAST-X 2026). Reston, USA: The Internet Society, 2026[2026-10-14]. DOI:10.14722/last-x.2026.23042.
[49] HUANG H, SHI J, CHEN J, et al. PenForge: On-the-fly expert agent construction for automated penetration testing[C]//ICSE-NIER '26: Proceedings of the IEEE/ACM 48th International Conference on Software Engineering. New York, USA: ACM, 2026: 76-80. DOI:10.1145/3786582.3786814.
[50] JIANG M, HUANG J, WANG J, et al. vEcho: A paradigm shift from vulnerability verification to proactive discovery with large language models[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2603.01154.
[51] WANG W, GU H, WU Z, et al. PTFusion: LLM-driven context-aware knowledge fusion for Web penetration testing[J]. Information Fusion, 2026, 127: 103731. DOI:10.1016/j.inffus.2025.103731.
[52] HAPPE A, CITO J. Can LLMs hack enterprise networks? Autonomous assumed breach penetration-testing Active Directory networks[J]. ACM Transactions on Software Engineering and Methodology, 2026, 35(6): 1-54. DOI:10.1145/3766895.
[53] DENG G, LIU Y, LI Y, et al. What makes a good LLM agent for real-world penetration testing?[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2602.17622.
[54] CHALLITA B, PARREND P. RedTeamLLM: An agentic AI framework for offensive security[C]//Artificial Intelligence for Sustainability and Global Security: IFIP WG 12.11 and WG 12.13 International Workshops, IJCAI 2025, Montréal, QC, Canada, August 16-17, 2025, Revised Selected Papers. IFIP Advances in Information and Communication Technology, vol. 780. Cham: Springer, 2026: 337-354. DOI:10.1007/978-3-032-21184-2_26.
[55] SINGER B, LUCAS K, ADIGA L, et al. Incalmo: An autonomous LLM-assisted system for red teaming multi-host networks[C]//2026 IEEE Symposium on Security and Privacy (SP). Washington D. C., USA: IEEE Press, 2026: 4282-4300. DOI:10.1109/SP63933.2026.00132.
[56] HE P, FOX A, MICULICICH L, et al. Co-RedTeam: Orchestrated security discovery and exploitation with LLM agents[EB/OL]. [2026-09-10]. https://arxiv.org/abs/2602.02164.
[57] LUO Z H, WANG P F, WANG B S, et al. VulHawk: Cross-architecture vulnerability detection with entropy-based binary code search[C/OL]//30th Annual Network and Distributed System Security Symposium (NDSS 2023). Reston, USA: The Internet Society, 2023. (2023-02-27)[2026-09-10]. DOI:10.14722/ndss.2023.24415.
[58] ZHOU X, WANG P, LIU C, et al. UltraFuzz: Towards resource-saving in distributed fuzzing[J]. IEEE Transactions on Software Engineering, 2023, 49(4): 2394-2412. DOI:10.1109/TSE.2022.3219520.
[59] LIU D, WANG P, ZHOU X, et al. From release to rebirth: Exploiting Thanos objects in Linux kernel[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 533-548. DOI:10.1109/TIFS.2022.3226906.
[60] 崔泽源, 葛文翰, 王俊峰. 基于大模型与强化学习的网络威胁狩猎方法[J]. 计算机工程, 2026, 52(10): 363-374. DOI:10.19678/j.issn.1000-3428.0070706.
CUI Z Y, GE W H, WANG J F. A cyber threat hunting method using reinforcement learning agent with large language models [J]. Computer Engineering, 2026, 52(10): 363-374. DOI:10.19678/j.issn.1000-3428.0070706. (in Chinese).
[61] 廖牛语, 田沄, 李岩松, 等. 大模型工具学习: 方法、作用与机制[J]. 计算机工程, 2025, 51(12): 1-17. DOI:10.19678/j.issn.1000-3428.0253230.
LIAO N Y, TIAN Y, LI Y S, et al. Tool learning with large language models: Methods, functions, and mechanisms[J]. Computer Engineering, 2025, 51(12): 1-17. DOI:10.19678/j.issn.1000-3428.0253230. (in Chinese).
|