Paper Citation Record · LEDGER

RedTeamLLM: an Agentic AI framework for offensive security

As of 16 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 3 inbound Pith citation observations for arXiv:2505.06913.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.06913 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:33:52.354999Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T12:00:05.330178Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-06-29T12:03:23.950682Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy13
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 13f25711-1d48-4d47-b19b-af510e19a96f · outbound

This paper cites Agentic ai: Au- tonomous intelligence for complex goals–a comprehen- sive survey.

RedTeamLLM: an Agentic AI framework for offensive security Agentic ai: Au- tonomous intelligence for complex goals–a comprehen- sive survey

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.879829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 301a4f14-9a2b-4388-bb0e-a9e20623b56c · outbound

This paper cites {PentestGPT}: Evaluating and harnessing large language models for automated penetration testing.

RedTeamLLM: an Agentic AI framework for offensive security {PentestGPT}: Evaluating and harnessing large language models for automated penetration testing

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.855094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9d4477b1-804e-4f38-9a34-483aae2c4489 · outbound

This paper cites Decoding the Threat Landscape : ChatGPT, FraudGPT, and WormGPT in Social Engineering Attacks.

RedTeamLLM: an Agentic AI framework for offensive security Decoding the Threat Landscape : ChatGPT, FraudGPT, and WormGPT in Social Engineering Attacks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.224563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bd7ad3e-1464-4aba-9233-1fa38b2f53ba · outbound

This paper cites LLM Agents can Autonomously Hack Websites.

RedTeamLLM: an Agentic AI framework for offensive security LLM Agents can Autonomously Hack Websites

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.234261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7cdacd9-c872-43cc-9bf6-c0a7f1b80a1d · outbound

This paper cites Countering Autonomous Cyber Threats.

RedTeamLLM: an Agentic AI framework for offensive security Countering Autonomous Cyber Threats

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.238622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6735345-73a8-40f3-8aa7-3c3e719d92d8 · outbound

This paper cites On the (In)Security of LLM App Stores.

RedTeamLLM: an Agentic AI framework for offensive security On the (In)Security of LLM App Stores

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.243074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 620f049b-238b-4f9b-8ae4-0afdc738500f · outbound

This paper cites Ai agents and agen- tic systems: A multi-expert analysis.

RedTeamLLM: an Agentic AI framework for offensive security Ai agents and agen- tic systems: A multi-expert analysis

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.842327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c04a5cd5-e13f-44e5-a069-069ae106d7d4 · outbound

This paper cites Toward robust secu- rity orchestration and automated response in security op- erations centers with a hyper-automation approach using agentic ai.

RedTeamLLM: an Agentic AI framework for offensive security Toward robust secu- rity orchestration and automated response in security op- erations centers with a hyper-automation approach using agentic ai

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.829108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8a0bf164-f41f-4680-9296-0bcc57a662e8 · outbound

This paper cites Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements.

RedTeamLLM: an Agentic AI framework for offensive security Towards Automated Penetration Testing: Introducing LLM Benchmark, Analysis, and Improvements

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.257217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 798f0f07-c628-40a7-974d-e5246b1ca133 · outbound

This paper cites DarkBERT: A Language Model for the Dark Side of the Internet.

RedTeamLLM: an Agentic AI framework for offensive security DarkBERT: A Language Model for the Dark Side of the Internet

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.261696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84e001e6-19d5-4d87-9d20-1f98089c6c7a · outbound

This paper cites Security Threats in Agentic AI System.

RedTeamLLM: an Agentic AI framework for offensive security Security Threats in Agentic AI System

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.266454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a06bd18f-d4b7-403f-90e9-f1d89f87045b · outbound

This paper cites Fun- tuning: Characterizing the vulnerability of proprietary llms to optimization-based prompt injection attacks via the fine-tuning interface.

RedTeamLLM: an Agentic AI framework for offensive security Fun- tuning: Characterizing the vulnerability of proprietary llms to optimization-based prompt injection attacks via the fine-tuning interface

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.813297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d488c06c-cbaa-4297-b715-0eed13e5a9fa · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.

RedTeamLLM: an Agentic AI framework for offensive security Retrieval-augmented generation for knowledge-intensive nlp tasks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.274951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70b4bac6-c61d-4858-b433-1912961f7448 · outbound

This paper cites Evocodebench: An evolving code generation benchmark with domain-specific evaluations.

RedTeamLLM: an Agentic AI framework for offensive security Evocodebench: An evolving code generation benchmark with domain-specific evaluations

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.791619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ca03be43-e2bf-4a38-b0bd-2b896172af59 · outbound

This paper cites Structured chain-of-thought prompting for code genera- tion.

RedTeamLLM: an Agentic AI framework for offensive security Structured chain-of-thought prompting for code genera- tion

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.776045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ae4267b0-3c9a-4088-a3bf-79de72cbcf00 · outbound

This paper cites Artificial intelligence (ai) cybersecurity dimensions: a comprehensive framework for understanding adversarial and offensive ai.

RedTeamLLM: an Agentic AI framework for offensive security Artificial intelligence (ai) cybersecurity dimensions: a comprehensive framework for understanding adversarial and offensive ai

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.762902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 934c8b65-e079-4c65-ad74-c0d2456bcabf · outbound

This paper cites HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing.

RedTeamLLM: an Agentic AI framework for offensive security HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.294731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91439987-562f-4ed3-a479-5ed70cd4e6a0 · outbound

This paper cites Agentic ai and the cyber arms race.

RedTeamLLM: an Agentic AI framework for offensive security Agentic ai and the cyber arms race

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.750862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 165e20cd-57ab-4907-9f7f-02843cd0f495 · outbound

This paper cites ADaPT: As-Needed Decomposition and Planning with Language Models.

RedTeamLLM: an Agentic AI framework for offensive security ADaPT: As-Needed Decomposition and Planning with Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.302316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c7dfe44-748e-4765-93b6-8e087731dc71 · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

RedTeamLLM: an Agentic AI framework for offensive security A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.306132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb47a308-7a52-420b-9300-39bc19784d04 · outbound

This paper cites Practices for governing agentic ai sys- tems.

RedTeamLLM: an Agentic AI framework for offensive security Practices for governing agentic ai sys- tems

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.736884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0e2e6e25-b83d-4066-b6ec-14c83f347d61 · outbound

This paper cites PentestAgent: Incorporating LLM Agents to Automated Penetration Testing.

RedTeamLLM: an Agentic AI framework for offensive security PentestAgent: Incorporating LLM Agents to Automated Penetration Testing

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.314821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21582dec-fad8-4891-955a-d43188fa7b30 · outbound

This paper cites PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents.

RedTeamLLM: an Agentic AI framework for offensive security PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.318771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021770e7-17e6-4a4c-9142-abb11aa60c08 · outbound

This paper cites TrustLLM: Trustworthiness in Large Language Models.

RedTeamLLM: an Agentic AI framework for offensive security TrustLLM: Trustworthiness in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.322665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe0790fe-70cf-47cd-b4d2-7eec7fa5ad69 · outbound

This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.

RedTeamLLM: an Agentic AI framework for offensive security CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.326946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bc64968-a760-42bc-aa4f-ead5edc28071 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

RedTeamLLM: an Agentic AI framework for offensive security Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.331077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c9130b-3477-48ab-9af9-7277dede907f · outbound

This paper cites Tdag: A multi-agent framework based on dynamic task decomposition and agent genera- tion.

RedTeamLLM: an Agentic AI framework for offensive security Tdag: A multi-agent framework based on dynamic task decomposition and agent genera- tion

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.724712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fee21d8c-31c0-40ce-86d9-270e7cc3ed66 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

RedTeamLLM: an Agentic AI framework for offensive security Chain-of-thought prompting elicits reasoning in large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.343190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dcbffbd-649b-45b9-b129-2fa9f6419b1a · outbound

This paper cites AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks.

RedTeamLLM: an Agentic AI framework for offensive security AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.347166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f114f6e3-4996-4d37-b12c-94b77cfbca6e · outbound

This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly.

RedTeamLLM: an Agentic AI framework for offensive security A survey on large language model (llm) security and privacy: The good, the bad, and the ugly

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.704492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cec682d3-bf0d-4d8d-9080-08f22fc33b02 · outbound

This paper cites Automatic Chain of Thought Prompting in Large Language Models.

RedTeamLLM: an Agentic AI framework for offensive security Automatic Chain of Thought Prompting in Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.354999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1a043a5-4cba-40fb-b925-188a291bd12b · outbound

This paper cites Chain of Code: Reasoning with a Language Model-Augmented Code Emulator.

RedTeamLLM: an Agentic AI framework for offensive security Chain of Code: Reasoning with a Language Model-Augmented Code Emulator

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.278924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a247f233-06a2-41c3-b00a-6936220a6bc1 · outbound

This paper cites TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation.

RedTeamLLM: an Agentic AI framework for offensive security TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.335624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3415ba6d-de8d-45d4-b3e2-d915ee0b72d1 · outbound

This paper cites LLM Agents can Autonomously Exploit One-day Vulnerabilities.

RedTeamLLM: an Agentic AI framework for offensive security LLM Agents can Autonomously Exploit One-day Vulnerabilities

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.229693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd4c45c7-06d3-47d0-8276-e4219afbac68 · outbound

This paper cites Breaking down the defenses: A comparative survey of attacks on large language models.

RedTeamLLM: an Agentic AI framework for offensive security Breaking down the defenses: A comparative survey of attacks on large language models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T22:33:52.216221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6931b171-cbe6-49bf-ab82-b211bfc220b9 · outbound

This paper cites When do program-of-thought works for reasoning? In Proceed- ings of the AAAI Conference on Artificial Intelligence, vol- ume 38, pages 17691–17699,.

RedTeamLLM: an Agentic AI framework for offensive security When do program-of-thought works for reasoning? In Proceed- ings of the AAAI Conference on Artificial Intelligence, vol- ume 38, pages 17691–17699,

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T22:33:52.866966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 2ed5c236-14f4-491c-92de-16f4d088dbd8 · inbound

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing cites this paper.

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing RedTeamLLM: an Agentic AI framework for offensive security

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:45:52.800364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 178a6576-2a25-475e-a7e9-de092d2b9932 · inbound

CyberAId: AI-Driven Cybersecurity for Financial Service Providers cites this paper.

CyberAId: AI-Driven Cybersecurity for Financial Service Providers RedTeamLLM: an Agentic AI framework for offensive security

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:21:06.896686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3d73d0f8-0128-4737-bd02-9bc45a8f211c · inbound

Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity? cites this paper.

Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity? RedTeamLLM: an Agentic AI framework for offensive security

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:03:23.952223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.