Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T15:23:53.609413Z
Paper Citation Record · LEDGER
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
As of 20 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 15 inbound Pith citation observations for arXiv:2505.17107.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-05T15:09:23.822820Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-04T19:20:07.172450Z
Reference resolution
69 of 69 outbound references displayed
- verified exact2
- verified fuzzy31
- unresolved35
- parse uncertain1
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation da73bbff-cdf3-4a14-9441-bfafda33a5a2 · outbound
This paper cites EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:49.354988Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 48f544f5-f6d7-45e7-82e0-80cd7b773e1d · outbound
This paper cites Sumona, Masud Mohiuddin, Md Tanzim Reza, and Md Mizanur Rahman.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Sumona, Masud Mohiuddin, Md Tanzim Reza, and Md Mizanur Rahman
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:59.806894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 72b2065f-d09d-46bd-a34c-ff85fcf586c8 · outbound
This paper cites Self-rag: Learning to retrieve, generate, and critique through self-reflection.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Self-rag: Learning to retrieve, generate, and critique through self-reflection
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:59.714401Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e131ed78-c713-4cac-8044-c207ca7ec5b8 · outbound
This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:49.535857Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c69097e5-9b39-4a40-ace7-209e81822318 · outbound
This paper cites RepairAgent: An Autonomous, LLM-Based Agent for Program Repair.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:49.609721Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c821d72f-2e16-4ee4-814d-3be3c564d635 · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:59.581545Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 2dd68dcd-dd76-4e0c-bb5e-2b38ef6ed593 · outbound
This paper cites Using facebook’s open source capture the flag platform as a hands-on learning and assessment tool for cybersecurity education.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Using facebook’s open source capture the flag platform as a hands-on learning and assessment tool for cybersecurity education
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:59.417416Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e2a80192-6cc9-46a6-8a25-34f47f053ecb · outbound
This paper cites DARPA cyber grand challenge.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution DARPA cyber grand challenge
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:59.308223Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation cf6be66a-2086-47d8-b398-7727b5cdad82 · outbound
This paper cites DARPA AIxCC.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution DARPA AIxCC
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:59.196565Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 685e9221-f920-43b4-ab64-c33c43009b15 · outbound
This paper cites PentestGPT: An LLM-empowered Automatic Penetration Testing Tool.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution PentestGPT: An LLM-empowered Automatic Penetration Testing Tool
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:49.977017Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 10b548e0-d17b-4400-aecc-bafd2220cf1b · outbound
This paper cites Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:50.059184Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3304230a-1de0-4f22-bc58-6fc0f109821a · outbound
This paper cites From rag to multi-agent systems: A survey of modern approaches in llm development, 2025.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution From rag to multi-agent systems: A survey of modern approaches in llm development, 2025
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:59.017186Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 97c5f05e-4e7a-42cd-86f5-1ea1567bfcfa · outbound
This paper cites Outside the comfort zone: Analysing LLM capabilities in software vulnerability detection.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Outside the comfort zone: Analysing LLM capabilities in software vulnerability detection
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:58.919046Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 1b02e5ee-5b70-4908-b288-c124534e385f · outbound
This paper cites GRAG: Graph Retrieval-Augmented Generation.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution GRAG: Graph Retrieval-Augmented Generation
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:50.274614Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e7f2b0a2-3c0b-4793-8a94-fabb27eb14b1 · outbound
This paper cites Matei, and Elisa Bertino.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Matei, and Elisa Bertino
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:58.761536Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation c2a6ae78-53a7-4f37-a962-9dad2f48e5bd · outbound
This paper cites A Study on the Implementation Method of an Agent-Based Advanced RAG System Using Graph.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution A Study on the Implementation Method of an Agent-Based Advanced RAG System Using Graph
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:50.387530Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 07356030-f6a0-4ec6-ac42-77386c30f29d · outbound
This paper cites Active retrieval augmented generation.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Active retrieval augmented generation
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:50.456667Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation feffb33a-7e27-49af-98d4-096e173a253a · outbound
This paper cites Long-context llms meet rag: Overcoming challenges for long inputs in rag.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Long-context llms meet rag: Overcoming challenges for long inputs in rag
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:58.646193Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation bdac6f80-8a38-4169-ada3-2cead6331af4 · outbound
This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Retrieval-augmented generation for knowledge-intensive nlp tasks
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:50.569125Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 574e6a8c-785f-460b-b986-0150e643a444 · outbound
This paper cites If LLMs Would Just Look: Simple Line-by-line Checking Improves Vulnerability Localization.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution If LLMs Would Just Look: Simple Line-by-line Checking Improves Vulnerability Localization
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:50.630110Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bcac0563-5120-4971-a3ad-fa030b868acf · outbound
This paper cites GRACE: Empowering LLM-based software vulnerability detection with graph structure and in-context learning.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution GRACE: Empowering LLM-based software vulnerability detection with graph structure and in-context learning
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:58.547853Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 641a404a-df5c-4d51-92d2-b97a4d541e6c · outbound
This paper cites Milvus | High-Performance Vector Database Built for Scale.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Milvus | High-Performance Vector Database Built for Scale
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:58.386059Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 02725189-fd51-4b75-b88c-0bd00bd0df81 · outbound
This paper cites HackSynth: LLM agent and evaluation framework for autonomous penetration testing, 2024.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution HackSynth: LLM agent and evaluation framework for autonomous penetration testing, 2024
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:58.131563Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 3d5a63b8-f777-437e-86ce-aa3a84e19426 · outbound
This paper cites Neo4j Graph Database & Analytics.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Neo4j Graph Database & Analytics
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:58.040705Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 2e2acc91-3ac7-42b4-8a51-8181b5fd34b9 · outbound
This paper cites Graph Retrieval-Augmented Generation: A Survey.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Graph Retrieval-Augmented Generation: A Survey
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:50.945679Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0382f042-3991-4982-9ef3-3586825e7e5c · outbound
This paper cites Friend or foe – the impact of ChatGPT on capture the flag competitions.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Friend or foe – the impact of ChatGPT on capture the flag competitions
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:57.898223Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation dd504d4b-2608-44c7-a750-792976e46ace · outbound
This paper cites Earp, Sven Nyholm, John Danaher, Nikolaj Møller, Hi- lary Bowman-Smart, Joshua Hatherley, Julian Koplin, Monika Plozza, Daniel Rodger, et al.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Earp, Sven Nyholm, John Danaher, Nikolaj Møller, Hi- lary Bowman-Smart, Joshua Hatherley, Julian Koplin, Monika Plozza, Daniel Rodger, et al
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:57.774940Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 74ff7217-9cec-4998-9b9d-5bbef8f13c7d · outbound
This paper cites A rag-based question-answering solution for cyber-attack investigation and attribution.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution A rag-based question-answering solution for cyber-attack investigation and attribution
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:57.635220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 81afa3f0-b5f2-4c00-9730-aad28ced18c5 · outbound
This paper cites A rag-based question-answering so- lution for cyber-attack investigation and attribution.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution A rag-based question-answering so- lution for cyber-attack investigation and attribution
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:57.506278Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 65cc2e4a-8cee-423d-a795-3f92eb440df0 · outbound
This paper cites ISBN 978-3-031-82361-9.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution ISBN 978-3-031-82361-9
Reference 30
- Resolution
- verified exact
- doi, observed 2026-08-07T15:23:53.724163Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 62362588-4ee9-4dd3-87b6-468428c4147d · outbound
This paper cites An Empirical Evaluation of LLMs for Solving Offensive Security Challenges.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution An Empirical Evaluation of LLMs for Solving Offensive Security Challenges
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:51.648562Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bd077f92-f469-40c9-9fe8-94e8b943e27d · outbound
This paper cites Savin, Ammar Asseri, Josiah Dykstra, Jonathan Goohs, Anthony Melaragno, and William Casey.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Savin, Ammar Asseri, Josiah Dykstra, Jonathan Goohs, Anthony Melaragno, and William Casey
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:57.402717Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 765fd2bc-8d44-40e1-9a46-5a34e78d7da0 · outbound
This paper cites PentestAgent: Incorporating LLM Agents to Automated Penetration Testing.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution PentestAgent: Incorporating LLM Agents to Automated Penetration Testing
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:51.808707Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8e16c597-e579-40f2-a727-a0151c7971b0 · outbound
This paper cites NYU CTF Bench: A scalable open-source benchmark dataset for evaluating LLMs in offensive security.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution NYU CTF Bench: A scalable open-source benchmark dataset for evaluating LLMs in offensive security
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:57.254998Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 2e9a5372-85b6-4dfb-b46e-45c49378f1e3 · outbound
This paper cites Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:51.936604Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 579d5766-0086-4214-925b-5b9a0218e2e8 · outbound
This paper cites MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T15:23:54.148469Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9486b6de-05d8-4924-b102-d61bbf131e61 · outbound
This paper cites MITRE ATT&CK.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution MITRE ATT&CK
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:56.917326Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4f278ae1-0d2e-4dd6-afa3-96923cd5f4d0 · outbound
This paper cites Seah, and Ee-Chien Chang.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Seah, and Ee-Chien Chang
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:57.121878Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 3fbf97f2-3eeb-4cbd-9642-901792e3597d · outbound
This paper cites D-CIPHER: Dynamic collaborative intelligent multi-agent system with planner and heterogeneous executors for offensive security,.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution D-CIPHER: Dynamic collaborative intelligent multi-agent system with planner and heterogeneous executors for offensive security,
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:56.742287Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fa9cc9eb-00d9-40c6-ac67-8e1fb4286ed3 · outbound
This paper cites Benefits and pitfalls of using capture the flag games in university courses.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Benefits and pitfalls of using capture the flag games in university courses
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.338536Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e4c0dbfd-6dea-440b-b8f1-693ff95caa74 · outbound
This paper cites Hacking CTFs with Plain Agents.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Hacking CTFs with Plain Agents
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.141714Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 51239530-b88f-4f27-a7ff-c3d7434f7089 · outbound
This paper cites Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.436481Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e9207ad7-6708-45ab-9791-502cd2a640a7 · outbound
This paper cites D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.289389Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 681d0976-9bba-41c0-9206-90befc5ca0a4 · outbound
This paper cites CodeRAG-Bench: Can Retrieval Augment Code Generation?.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution CodeRAG-Bench: Can Retrieval Augment Code Generation?
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.512872Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8bcad79c-df99-4b6d-89a3-4e73b6a82503 · outbound
This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.392341Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9cb87a5e-bedf-4346-b01a-e0520762c89d · outbound
This paper cites Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:56.425890Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7149bc8c-edcb-4b94-9f3e-70e9bb1ba64d · outbound
This paper cites Searching for best practices in retrieval- augmented generation.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Searching for best practices in retrieval- augmented generation
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:56.569637Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 91577c1f-800f-42e3-aceb-ed37f898a3fa · outbound
This paper cites Autopwn: Artifact- assisted heap exploit generation for ctf pwn competitions.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Autopwn: Artifact- assisted heap exploit generation for ctf pwn competitions
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.756126Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a48ec4be-b2b3-40df-bf1a-dc9b3a70cd80 · outbound
This paper cites Unveiling security, privacy, and ethical concerns of ChatGPT.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unveiling security, privacy, and ethical concerns of ChatGPT
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.583484Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49e9f774-98fe-4e91-8300-04e9e11dd8a1 · outbound
This paper cites Narasimhan, and Yuan Cao.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Narasimhan, and Yuan Cao
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:55.983574Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fed882d2-7b42-4231-9a77-01b2a44fe716 · outbound
This paper cites ReWOO: Decoupling reasoning from observations for efficient augmented language models,.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution ReWOO: Decoupling reasoning from observations for efficient augmented language models,
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:56.279742Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 20c84187-f7f1-45b9-a28e-d983bf409629 · outbound
This paper cites ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.706593Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4d86cefd-68c7-40d8-bedd-af030a00058d · outbound
This paper cites step-back.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution step-back
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.982078Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 77939990-c971-4d9e-b02a-06b75695966a · outbound
This paper cites Narasimhan.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Narasimhan
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:56.143560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9c21991c-eadb-487d-9a76-7927a1c1cf7b · outbound
This paper cites Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.914666Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d8d6db6-e353-4b05-a88d-3d2331d29026 · outbound
This paper cites An empirical study of automated vulnerability localization with large language models, 2024.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution An empirical study of automated vulnerability localization with large language models, 2024
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.961532Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a9b24590-9861-4947-8ad4-4cf0009b2164 · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 59
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:55.891831Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4206e170-4bd8-48f2-a1ff-35432a223be0 · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 60
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:55.765223Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d18192c7-1b01-4fc4-a042-826d6a281328 · outbound
This paper cites yes" or “no.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution yes" or “no
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:55.609551Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 37a43cc8-a9b5-48ae-b06e-6fba3392f97d · outbound
This paper cites dogestore.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution dogestore
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:55.490866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ddb24aa2-1745-4fcb-b573-046ca8287527 · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 63
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:55.352456Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 975ed18b-9b58-4a7f-9552-14de08f7fd3a · outbound
This paper cites hack-tac-toe.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution hack-tac-toe
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:55.211279Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e38298ca-722c-4169-a8e7-2c39c27af735 · outbound
This paper cites journey2.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution journey2
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:23:55.022755Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 6ac2b2e4-4a3c-4d52-b13e-67dc09ecefa8 · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 66
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:54.929102Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ed20caff-df95-4164-b14f-b5536ea7c399 · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 67
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:54.705433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a7be2c4e-2c0c-4e05-8e66-8cd011b6ea2c · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 68
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:54.555664Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 1564de74-2725-40a1-947e-6832612bac85 · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 69
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:23:54.405981Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 349dffc6-f783-43e7-8e06-d78707229650 · outbound
This paper cites Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:23:52.023681Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2462d0bd-c946-47dc-ba9d-c1ca7a1f074f · outbound
This paper cites an unresolved cited work.
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution Unresolved cited work
Reference 2025
- Resolution
- parse uncertain
- raw_fallback, observed 2026-08-07T15:23:58.290651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Pith citing papers
Observation 5770272e-8cfe-4254-bd57-192e9e765f5d · inbound
Ransomware 3.0: Self-Composing and LLM-Orchestrated cites this paper.
Ransomware 3.0: Self-Composing and LLM-Orchestrated CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T15:09:23.822820Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a1693e07-42de-44bf-889c-eaf38d71ce4b · inbound
Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks cites this paper.
Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T06:06:19.089932Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9211b24d-6d3d-4eef-a151-b1a067a3f47e · inbound
RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs cites this paper.
RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T11:55:21.296590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 6da21fe0-160d-45c2-ae77-2b0bb6daa078 · inbound
Dynamic Cyber Ranges cites this paper.
Dynamic Cyber Ranges CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 57
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T22:16:53.098373Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fb0762c0-90d7-4910-a6e1-eaa36b02a133 · inbound
CrackMeBench: Binary Reverse Engineering for Agents cites this paper.
CrackMeBench: Binary Reverse Engineering for Agents CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:56:43.617350Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation f045a344-285e-4756-ab2b-08590d883372 · inbound
CTFusion: A CTF-based Benchmark for LLM Agent Evaluation cites this paper.
CTFusion: A CTF-based Benchmark for LLM Agent Evaluation CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:37:03.329138Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 394a1dd2-40c8-4317-b960-2d13a2b14ede · inbound
Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries cites this paper.
Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 44
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T14:05:54.718136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 2f7ddcf5-86aa-48bb-822c-4f0e722890dc · inbound
Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries cites this paper.
Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T16:46:36.842198Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cf8b89a1-66b1-47ec-ad59-8d628269940b · inbound
Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries cites this paper.
Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T14:03:38.099605Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 07d196ab-a338-4368-8150-1e4dd948eee4 · inbound
uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs cites this paper.
uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-05-19T15:47:38.558602Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 42b5409f-6093-4edd-85c5-2aba6bccf260 · inbound
CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly cites this paper.
CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T21:23:58.998425Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation c3a51424-c657-47d7-b36b-da881eb27a36 · inbound
HunterAgent: Neuro-Symbolic Attack Trace Reconstruction under Anti-Forensics cites this paper.
HunterAgent: Neuro-Symbolic Attack Trace Reconstruction under Anti-Forensics CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T07:13:17.094784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 92c01765-6e0d-4fd3-92ff-0937a3281891 · inbound
Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots cites this paper.
Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T07:03:12.694554Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 61d44630-684e-4486-8c68-4a5bd23404cb · inbound
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing cites this paper.
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 11
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-04T19:20:07.173913Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 5e0157f5-8fa0-4e61-ae8f-ed42ee490ed9 · inbound
Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI cites this paper.
Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T06:28:52.906906Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.