Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) | Paper Citation Record

Observation e9e9ffb8-750e-4b83-8c2f-bd45f20644c3 · outbound

This paper cites https://www.atomicredteam.io/.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) https://www.atomicredteam.io/

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.297825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 55d89643-12c0-4fe2-b587-e12a11e90d67 · outbound

This paper cites https://aicyberchallenge.com/ overview/.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) https://aicyberchallenge.com/ overview/

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.288443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 01e142a8-f26c-45f9-9bbe-4eb79a5a53e1 · outbound

This paper cites https://attack.mitre.org/.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) https://attack.mitre.org/

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.279178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 79f9f41b-f184-4565-abc2-5c6a8e94bdcd · outbound

This paper cites EnIGMA: Interactive tools substantially assist LM agents in finding security vulnerabilities.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) EnIGMA: Interactive tools substantially assist LM agents in finding security vulnerabilities

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.270066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 067df76b-02b2-4127-a1bc-ba247e54a6f4 · outbound

This paper cites Back to basics: Revisiting REINFORCE-style optimization for learning from human feedback in LLMs.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Back to basics: Revisiting REINFORCE-style optimization for learning from human feedback in LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.176790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 141545ae-3ce0-4a1b-9c95-bb69a16af683 · outbound

This paper cites Ctibench: a benchmark for evaluating llms in cyber threat intelligence.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Ctibench: a benchmark for evaluating llms in cyber threat intelligence

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.255302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 489af948-f565-4c76-9a3a-e2ed8ea9bf0b · outbound

This paper cites Claude Mythos Preview red.anthropic.com — red.anthropic.com.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Claude Mythos Preview red.anthropic.com — red.anthropic.com

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.245978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a94a278f-1b97-4c27-a052-f8d65eea29d9 · outbound

This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.189295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cdc2bd7-d8d6-4bb1-8996-da6ea68649a7 · outbound

This paper cites Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.193944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66b4479a-f346-4677-b5e0-5a1b4346697f · outbound

This paper cites Large language models are autonomous cyber defenders.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Large language models are autonomous cyber defenders

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.236818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eafcbef2-bf1a-42ce-8839-962fd2b7ef32 · outbound

This paper cites Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.200744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f56c22bb-c346-46b6-a51d-8999397414a7 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Training Verifiers to Solve Math Word Problems

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.203952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44250ce-64e6-41b6-9e34-c9837de6b25f · outbound

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

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) PentestGPT: Evaluating and harnessing large language models for automated penetration testing

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.222351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 20e8ebcb-43a6-4c2f-9524-793b567730e6 · outbound

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

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) LLM Agents can Autonomously Exploit One-day Vulnerabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.210586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d7de844-f4f5-43d7-aa20-28fb6659842a · outbound

This paper cites LLM Agents can Autonomously Hack Websites.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) LLM Agents can Autonomously Hack Websites

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.213871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 537a98f3-3e25-4ac9-9f28-20ec16beef8b · outbound

This paper cites Graphplanner: Graph- based agentic routing for LLMs.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Graphplanner: Graph- based agentic routing for LLMs

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.213523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d073036-155f-4786-b95f-11dcadf22c59 · outbound

This paper cites Redcode: Risky code execution and generation benchmark for code agents.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Redcode: Risky code execution and generation benchmark for code agents

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.203990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 39a0136a-f926-47b7-a4fa-5a049b9ef4b5 · outbound

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

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.223565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 392eb2c5-267a-48d7-8cfd-b33f5b60f0b6 · outbound

This paper cites Getting pwn’d by ai: Penetration testing with large language models.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Getting pwn’d by ai: Penetration testing with large language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.193871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c775929a-b989-4410-9ac8-1cc62c818250 · outbound

This paper cites Llms as hackers: Autonomous linux privilege escalation attacks.Empirical Software Engineering, 31(3):70, 2026.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Llms as hackers: Autonomous linux privilege escalation attacks.Empirical Software Engineering, 31(3):70, 2026

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.183206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a9a08bcc-f95d-4e36-9e3e-b8c4f572151a · outbound

This paper cites Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing reasoning.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing reasoning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.173065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c10c72e4-b6db-44d3-b056-381995d46494 · outbound

This paper cites Qwen2.5-Coder Technical Report.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Qwen2.5-Coder Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.236382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84a5e156-aac6-4e3a-88ed-2c2efa7cef9b · outbound

This paper cites GPT-4o System Card.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) GPT-4o System Card

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.239797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28054fda-b27f-4aaf-8f4b-81dd9ae96b37 · outbound

This paper cites Agentic ai for cyber defense: Llm-guided hierarchical multi-agent reinforcement learning.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Agentic ai for cyber defense: Llm-guided hierarchical multi-agent reinforcement learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.160033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 828afaeb-c042-4d3c-8910-8c58d6057b1c · outbound

This paper cites Search-r1: Training LLMs to reason and leverage search engines with reinforcement learning.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Search-r1: Training LLMs to reason and leverage search engines with reinforcement learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:18.148367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5157025d-7461-46e7-b441-5d66539fec3a · outbound

This paper cites Exploring the efficacy of multi-agent reinforcement learning for autonomous cyber defence: A cage challenge 4 perspective.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Exploring the efficacy of multi-agent reinforcement learning for autonomous cyber defence: A cage challenge 4 perspective

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.249096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e1b05a-f842-4dbb-b1e7-d144c3b9786f · outbound

This paper cites Automated cyber defense with generalizable graph-based reinforcement learning agents.arXiv preprint arXiv:2509.16151, 2025.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Automated cyber defense with generalizable graph-based reinforcement learning agents.arXiv preprint arXiv:2509.16151, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.252347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea105c7-6006-490e-be8b-80e29d897860 · outbound

This paper cites Large language models are zero-shot reasoners.Advances in neural information processing systems, 35:22199–22213, 2022.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Large language models are zero-shot reasoners.Advances in neural information processing systems, 35:22199–22213, 2022

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.255777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002fa239-7cad-40a3-9abc-bd5b8d3cfe68 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Gonzalez, Hao Zhang, and Ion Stoica

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.258881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9181f4b-d3ac-47de-9116-2de7e18ab6a0 · outbound

This paper cites In-the-flow agentic system optimization for effective planning and tool use.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) In-the-flow agentic system optimization for effective planning and tool use

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.910451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 122e0f90-d9be-4245-9c27-eee78120d9bd · outbound

This paper cites Code as policies: Language model programs for embodied control.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Code as policies: Language model programs for embodied control

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.264984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74634654-66b4-4099-b9a5-9ac2f6dd52b0 · outbound

This paper cites Et-bert: A contextualized datagram representation with pre-training transformers for encrypted traffic classification.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Et-bert: A contextualized datagram representation with pre-training transformers for encrypted traffic classification

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.896149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 602324bb-d5ad-459d-9e75-1357f935d447 · outbound

This paper cites Cyberbench: A multi-task benchmark for evaluating large language models in cybersecurity.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Cyberbench: A multi-task benchmark for evaluating large language models in cybersecurity

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.886939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7addd55e-ce6c-400f-837c-9d12548168d0 · outbound

This paper cites Visual-rft: Visual reinforcement fine-tuning.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Visual-rft: Visual reinforcement fine-tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.273922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe77814f-b49e-4ca1-a9d0-27a9fc5cc743 · outbound

This paper cites Contrasting centralized and decentralized critics in multi-agent reinforcement learning.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Contrasting centralized and decentralized critics in multi-agent reinforcement learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.872569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3113a622-7603-43f8-a95c-d5faabd251b3 · outbound

This paper cites Eureka: Human-level reward design via coding large language models.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Eureka: Human-level reward design via coding large language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.279999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19bfc18e-0300-400e-9f37-06b0db33acbd · outbound

This paper cites Ray: A distributed framework for emerging {AI} applications.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Ray: A distributed framework for emerging {AI} applications

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.283080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3457e4e5-f661-4b23-8580-db69c17dbeaf · outbound

This paper cites Experience with emerald to date.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Experience with emerald to date

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.853501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bbccf353-cf5e-42ab-b437-e87fa106e2e5 · outbound

This paper cites Towards a high fidelity training environment for autonomous cyber defense agents.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Towards a high fidelity training environment for autonomous cyber defense agents

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.843871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6de97952-a83d-4464-a26e-8cf90eb500df · outbound

This paper cites Proximal Policy Optimization Algorithms.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Proximal Policy Optimization Algorithms

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.292586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a004ecfb-09e6-44c3-986f-43b6cbf9ea81 · outbound

This paper cites Nyu ctf bench: A scalable open-source benchmark dataset for evaluating llms in offensive security.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Nyu ctf bench: A scalable open-source benchmark dataset for evaluating llms in offensive security

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.834168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a10cc6c-cbfd-46c2-a99b-629db9076462 · outbound

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

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.298765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97c601a8-7810-4d7f-93d1-c46ca867f66b · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Hybridflow: A flexible and efficient rlhf framework

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.301997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6fbeb53-181b-4e61-9d1c-dbe37dd0d1ce · outbound

This paper cites Hierarchical multi-agent reinforcement learning for cyber network defense.Reinforcement Learning Journal, 6:790–810, 2025.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Hierarchical multi-agent reinforcement learning for cyber network defense.Reinforcement Learning Journal, 6:790–810, 2025

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.819801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d1bded1-97d5-40eb-8495-315f36c22d2b · outbound

This paper cites A taxonomy of intrusion response systems.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) A taxonomy of intrusion response systems

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.810253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2f99b4cb-176e-44b6-8d9e-9af9daa5eac8 · outbound

This paper cites Redsage: A cybersecurity generalist LLM.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Redsage: A cybersecurity generalist LLM

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.800806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 294053bb-943e-470b-9ada-fd18ddb5bad4 · outbound

This paper cites Cyberbattlesim, 2021.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Cyberbattlesim, 2021

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.791420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1782e2f7-4dd3-4e2a-9cab-129cb7519f89 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Qwen2.5: A party of foundation models, September 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.317755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52f80ab4-0d91-46e9-be5e-44d05215a9f5 · outbound

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

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.320654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c66d7f38-f65f-4667-bcd0-2e9622ff5b4e · outbound

This paper cites SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.324049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c23d796-9356-45ec-a517-60c7e6bfa970 · outbound

This paper cites SymRTLO: Enhancing RTL code optimization with LLMs and neuron-inspired symbolic reasoning.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) SymRTLO: Enhancing RTL code optimization with LLMs and neuron-inspired symbolic reasoning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.776191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5dfeadbe-4bab-4196-a7e0-b38991215f8c · outbound

This paper cites Cyber- gym: Evaluating AI agents’ real-world cybersecurity capabilities at scale.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Cyber- gym: Evaluating AI agents’ real-world cybersecurity capabilities at scale

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.330596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d765deb-4598-47d6-9abe-0b9c9fe38835 · outbound

This paper cites SWE-RL: Advancing LLM reasoning via reinforcement learning on open software evolution.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) SWE-RL: Advancing LLM reasoning via reinforcement learning on open software evolution

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.762294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7967ed37-304e-4d30-8fef-a0d5f8595db7 · outbound

This paper cites Autogen: Enabling next-gen LLM applications via multi-agent conversations.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Autogen: Enabling next-gen LLM applications via multi-agent conversations

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.752947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eee7a847-1c5c-464e-8a27-af119d650e66 · outbound

This paper cites Qwen2 Technical Report.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Qwen2 Technical Report

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.339747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3698d0f-5488-44a5-81a1-c9642f22a97c · outbound

This paper cites Intercode: Standardizing and benchmarking interactive coding with execution feedback.Advances in Neural Information Processing Systems, 36:23826–23854, 2023.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Intercode: Standardizing and benchmarking interactive coding with execution feedback.Advances in Neural Information Processing Systems, 36:23826–23854, 2023

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.343099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1dc883e-3319-46a9-bdee-54080f81ded9 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) React: Synergizing reasoning and acting in language models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.346037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e522d46-fdde-43c2-bcf0-37c6e7d88933 · outbound

This paper cites Primus: A pioneering collection of open-source datasets for cybersecurity LLM training.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Primus: A pioneering collection of open-source datasets for cybersecurity LLM training

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.734052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1caec6f9-8983-4b60-8d5d-737a854fc042 · outbound

This paper cites ACECODER: Acing coder RL via automated test-case synthesis.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) ACECODER: Acing coder RL via automated test-case synthesis

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.724919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 367b9b5e-445a-46ef-b1b6-e52272cd4fa2 · outbound

This paper cites Ho, and Percy Liang.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Ho, and Percy Liang

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:17.354780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13fc7108-c6b0-42d2-9814-7d4992243321 · outbound

This paper cites Abdi, William Blum, and Muhammad Abdul-Mageed.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Abdi, William Blum, and Muhammad Abdul-Mageed

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.710547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e13e38df-282a-43f7-a6e7-425f58fe3047 · outbound

This paper cites Yet another traffic classifier: A masked autoencoder based traffic transformer with multi- level flow representation.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Yet another traffic classifier: A masked autoencoder based traffic transformer with multi- level flow representation

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.700836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ad2c876-7da4-447a-9c50-02f548644f98 · outbound

This paper cites Curran Associates Inc., Red Hook, NY , USA, 2019.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Curran Associates Inc., Red Hook, NY , USA, 2019

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.690889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7c3dd15d-4a6b-4b36-974e-70e9254d75d6 · outbound

This paper cites More than just functional: LLM-as-a-critique for efficient code generation.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) More than just functional: LLM-as-a-critique for efficient code generation

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.681374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9750a2ff-fd21-4e2c-8c61-455322623ec2 · outbound

This paper cites CVE-bench: A benchmark for AI agents’ ability to exploit real-world web application vulnerabilities.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) CVE-bench: A benchmark for AI agents’ ability to exploit real-world web application vulnerabilities

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.671444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bf259fbf-ae1a-4a4e-8ced-017136dbe910 · outbound

This paper cites Teams of LLM agents can exploit zero-day vulnerabilities.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Teams of LLM agents can exploit zero-day vulnerabilities

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:58:17.661621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c46cf609-583b-4ba5-b8a1-54ebd9e9fbf7 · outbound

This paper cites Cyber-zero: Training cybersecurity agents without runtime.

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Cyber-zero: Training cybersecurity agents without runtime

Reference 67

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T19:58:17.476910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers