{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T09:08:52Z","timestamp":1784365732080,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234226","type":"print"},{"value":"9789819234233","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3423-3_49","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T08:45:32Z","timestamp":1784364332000},"page":"607-618","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5272-2468","authenticated-orcid":false,"given":"Liwei","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3417-1147","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6873-5710","authenticated-orcid":false,"given":"Ming","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1172-050X","authenticated-orcid":false,"given":"Ge","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2091-7732","authenticated-orcid":false,"given":"Yan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"49_CR1","unstructured":"Deng, G., et al.: {PentestGPT}: evaluating and harnessing large language models for automated penetration testing. In: 33rd USENIX Security Symposium (USENIX Security 2024), pp. 847\u2013864 (2024)"},{"key":"49_CR2","unstructured":"Fang, R., Bindu, R., Gupta, A., Kang, D.: LLM agents can autonomously exploit one-day vulnerabilities. arXiv preprint arXiv:2404.08144 (2024)"},{"key":"49_CR3","unstructured":"Fang, R., Bindu, R., Gupta, A., Zhan, Q., Kang, D.: LLM agents can autonomously hack websites. arXiv preprint arXiv:2402.06664 (2024)"},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Gong, R., et al.: Mindagent: emergent gaming interaction. In: Findings of the Association for Computational Linguistics: NAACL 2024, pp. 3154\u20133183 (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.200"},{"key":"49_CR5","unstructured":"Happe, A., Cito, J.: Benchmarking practices in LLM-driven offensive security: Testbeds, metrics, and experiment design. arXiv preprint arXiv:2504.10112 (2025)"},{"key":"49_CR6","unstructured":"Henke, J.: Autopentest: enhancing vulnerability management with autonomous LLM agents. arXiv preprint arXiv:2505.10321 (2025)"},{"key":"49_CR7","unstructured":"Khati, D., Rodriguez-Cardenas, D., Pantzer, P., Poshyvanyk, D.: Detecting and correcting hallucinations in LLM-generated code via deterministic AST analysis. arXiv preprint arXiv:2601.19106 (2026)"},{"key":"49_CR8","unstructured":"Khule, T.: STAF: leveraging LLMs for automated attack tree-based security test generation. The University of Western Ontario (Canada) (2024)"},{"key":"49_CR9","unstructured":"Liu, X., et al.: Agentbench: evaluating LLMs as agents. In: International Conference on Learning Representations, vol. 2024, pp. 52989\u201353046 (2024)"},{"key":"49_CR10","unstructured":"Qin, Y., et al.: Toolllm: facilitating large language models to master 16000+ real-world APIs. In: International Conference on Learning Representations, vol. 2024, pp. 9695\u20139717 (2024)"},{"key":"49_CR11","unstructured":"Shao, M., et al.: Craken: cybersecurity LLM agent with knowledge-based execution. arXiv preprint arXiv:2505.17107 (2025)"},{"key":"49_CR12","doi-asserted-by":"publisher","first-page":"8634","DOI":"10.52202\/075280-0377","volume":"36","author":"N Shinn","year":"2023","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: language agents with verbal reinforcement learning. Adv. Neural. Inf. Process. Syst. 36, 8634\u20138652 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"49_CR13","doi-asserted-by":"crossref","unstructured":"Singer, B., Lucas, K., Adiga, L., Jain, M., Bauer, L., Sekar, V.: Incalmo: an autonomous LLM-assisted system for red teaming multi-host networks. arXiv preprint arXiv:2501.16466 (2025)","DOI":"10.1109\/SP63933.2026.00132"},{"key":"49_CR14","unstructured":"Tung, I.K., Shi, Y.X., Chien, A., Liu, W., Zheng, L.: Aegis: white-box attack path generation using LLMs and training effectiveness evaluation for large-scale cyber defence exercises. arXiv preprint arXiv:2601.22720 (2026)"},{"key":"49_CR15","unstructured":"Vangeli, M., Brynielsson, J., Cohen, M., Kamrani, F.: Context relay for long-running penetration-testing agents"},{"issue":"3","key":"49_CR16","first-page":"38","volume":"3","author":"H Wang","year":"2025","unstructured":"Wang, H., Wang, Q., Guo, Y., Zhang, Q., Wang, C., Zhou, M.: A survey on automatic exploitation for offensive and defensive cyber operations. J. Cybersecur. 3(3), 38\u201356 (2025)","journal-title":"J. Cybersecur."},{"issue":"16","key":"49_CR17","doi-asserted-by":"publisher","first-page":"9096","DOI":"10.3390\/app15169096","volume":"15","author":"X Wu","year":"2025","unstructured":"Wu, X., et al.: Curriculumpt: LLM-based multi-agent autonomous penetration testing with curriculum-guided task scheduling. Appl. Sci. 15(16), 9096 (2025)","journal-title":"Appl. Sci."},{"key":"49_CR18","unstructured":"Xu, J., et al.: Autoattacker: a large language model guided system to implement automatic cyber-attacks. arXiv preprint arXiv:2403.01038 (2024)"},{"key":"49_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, M., et al.: Characterizing network threats against industrial control systems using honeypot technology. In: International Conference on Networking and Network Applications (NaNA), pp. 451\u2013457 (2025)","DOI":"10.1109\/NaNA66698.2025.00078"},{"key":"49_CR20","doi-asserted-by":"crossref","unstructured":"Zhou, M., Zheng, Z., Zhang, P., Lu, S., Xie, Y., Jin, Z.: Securenet-awmi: safeguarding network with optimal feature selection algorithm. In: IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), pp. 1506\u20131511 (2024)","DOI":"10.1109\/TrustCom63139.2024.00208"},{"key":"49_CR21","unstructured":"Zhou, S., et al.: Webarena: a realistic web environment for building autonomous agents. In: International Conference on Learning Representations, vol. 2024, pp. 15585\u201315606 (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3423-3_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T08:45:35Z","timestamp":1784364335000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3423-3_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819234226","9789819234233"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3423-3_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}