Paper Citation Record · LEDGER

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

As of 16 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 2 inbound Pith citation observations for arXiv:2506.02048.

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

pith.paper-citation-record.v1
2506.02048 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:02:35.466750Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T12:07:49.656453Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

35 of 35 outbound references displayed

verified exact1
verified fuzzy16
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation fa95b339-a0e1-4a06-9995-5bf3b0899e33 · outbound

This paper cites an unresolved cited work.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.388647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a64b9f8-2ce1-48d3-8b79-ff9e7372d2f9 · outbound

This paper cites LLM Agents can Autonomously Hack Websites.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges LLM Agents can Autonomously Hack Websites

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.391491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c849b5b3-9a78-4edd-a3ce-a0d2fa71b1b1 · outbound

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

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges LLM Agents can Autonomously Exploit One-day Vulnerabilities

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.394058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f3342ef-e9b4-4c1d-bcb0-a7af2fb80572 · outbound

This paper cites Teams of LLM Agents can Exploit Zero-Day Vulnerabilities.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.396718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d5dc54c-603a-452c-8238-74877666b44e · outbound

This paper cites an unresolved cited work.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:02:35.706042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b8433a1f-db6f-44a2-973e-4a657cf4068e · outbound

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

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.401593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d163595e-7ebc-4faf-a91d-e25a6264d473 · outbound

This paper cites NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.404055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7718ec-e1a9-48e5-92f1-5b9dca55f357 · outbound

This paper cites Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.406709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d08c128a-540e-4610-a949-cf42fcb8faf3 · outbound

This paper cites an unresolved cited work.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:02:35.698882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e8ed4256-efdb-435a-86d0-97e2ce8f940c · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.411104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3c486ee-fd75-4eb6-935d-bee858c388fc · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.413594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f304b23a-89b7-45dd-8787-438e66921a2f · outbound

This paper cites 1-8B-Instruct, 2024.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges 1-8B-Instruct, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.691624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a650f72c-7905-4486-9246-e85a5588b093 · outbound

This paper cites Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.418518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef6cafc-a7e0-428b-af97-083345b4c72b · outbound

This paper cites PentestGPT: An LLM-empowered Automatic Penetration Testing Tool.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.420795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1f2d8c-9178-4981-915e-101501c0aaf9 · outbound

This paper cites an unresolved cited work.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:02:35.683997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e4a46e96-a38f-418b-a752-da35882d7223 · outbound

This paper cites URL: https://platform.openai.com/ docs/guides/function-calling, accessed: 2025-05-28.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges URL: https://platform.openai.com/ docs/guides/function-calling, accessed: 2025-05-28

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.676718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation eb4c0bd1-bc1e-4ee1-be55-24d2cb1cdf17 · outbound

This paper cites URL: https://www.anthropic.com/news/model-context-protocol, accessed: 2025-05-28.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges URL: https://www.anthropic.com/news/model-context-protocol, accessed: 2025-05-28

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.669486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9cfb5d56-476f-4630-ba35-70a77b042409 · outbound

This paper cites Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.429250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df4f9eb9-7625-4771-ab55-3dd08100d03a · outbound

This paper cites Proximal Policy Optimization Algorithms.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Proximal Policy Optimization Algorithms

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:02:35.431731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04c3d49e-c949-416e-8d5e-38992414135d · outbound

This paper cites Ouyang, J.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Ouyang, J

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.662626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 55ebcec7-faf9-4d9a-8be5-7b373e70a166 · outbound

This paper cites Dettmers, A.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Dettmers, A

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.655915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6834854a-3dcf-426d-8b4a-4e6f000f5704 · outbound

This paper cites AICrypto: Evaluating Cryptography Capabilities of Large Language Models.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges AICrypto: Evaluating Cryptography Capabilities of Large Language Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:02:35.491580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ee495015-8739-4612-8855-2b1eb5c8bb6c · outbound

This paper cites Accessed: 2025-05-28.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Accessed: 2025-05-28

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.649128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4ed65a50-80c6-4c5b-8f85-d98d31775c57 · outbound

This paper cites 1-70B-Instruct, 2024.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges 1-70B-Instruct, 2024

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.642433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3a30f6db-1837-41f3-9126-252c3552c2c8 · outbound

This paper cites Accessed: 2025-05-28.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Accessed: 2025-05-28

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.636112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8d26589d-bc1c-4525-8a7d-fdaaf84358c1 · outbound

This paper cites Accessed: 2025-05-28.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Accessed: 2025-05-28

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.629552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f8c7f1b5-0c0c-4e5d-b517-1dcffd2f5e99 · outbound

This paper cites an unresolved cited work.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:02:35.622828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 52526601-282f-4b35-9150-d2a2d37060ef · outbound

This paper cites Schick, J.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Schick, J

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.616563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1b7d647e-c5c3-4b68-9580-0b3b88f47113 · outbound

This paper cites an unresolved cited work.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:02:35.610339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 13133585-3972-40d7-9026-8958a1a230e3 · outbound

This paper cites Greshake, S.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Greshake, S

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.603791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 301f1fce-1070-456c-a0f0-94cada55ab94 · outbound

This paper cites </reasoning> tags.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges </reasoning> tags

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.596857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5e0fcd20-e7db-47ad-b7ea-4909f8751a90 · outbound

This paper cites name": "execute_python.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges name": "execute_python

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.590219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e17357c6-677a-4135-a702-f7710af053d3 · outbound

This paper cites Wrap the final flag in\boxed{flag{...}}.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Wrap the final flag in\boxed{flag{...}}

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.583773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ecd17eef-c375-40ba-b49c-514d6d1ac55f · outbound

This paper cites Only write the boxed flagafter the tool’s reply (role="tool") has appeared.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges Only write the boxed flagafter the tool’s reply (role="tool") has appeared

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.577357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 968fe1e8-ea31-402a-95c3-46bf0eb29841 · outbound

This paper cites A vailable tools MCP_TOOL_LIST Question: QUESTION.

Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges A vailable tools MCP_TOOL_LIST Question: QUESTION

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:02:35.570547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation b6e5e358-173b-417b-bc16-3c5d10b9eff6 · inbound

Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations cites this paper.

Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-16T07:27:31.463153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4651da1b-586a-412b-a5cb-8d106f7d7fc5 · inbound

Cybersecurity AI (CAI) Dataset cites this paper.

Cybersecurity AI (CAI) Dataset Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.833206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.