paper-with-me

홈 › Papers

Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks

2026-04-18 · Tyler H. Merves, Michael H. Conaway, Joseph M. Escobar, Hakan T. Otal, Unal Tatar arxiv

We present, to our knowledge, the most comprehensive cross-model evaluation of LLM agents on offensive cybersecurity tasks, benchmarking 10 frontier models from 7 providers on all 200 challenges of the NYU CTF Bench. Building on the D-CIPHER multi-agent framework, we extend it with multi-provider backend support, a custom Kali Linux environment with over 100 pre-installed penetration testing tools, and runtime tool-discovery agents. Through a controlled factorial study, we find that the Kali Linux environment yields a +9.5 percentage-point improvement over Ubuntu, while auto-prompting and category-specific tips often degrade performance in well-equipped environments. Among models, Claude 4.5 Opus achieves the highest solve rate (59%), followed by Gemini 3 Pro (52%), with Gemini 3 Flash offering the best cost-efficiency at $0.05 per solve. Asymmetric planner/executor model assignments provide no meaningful benefit while coherent same-model configurations consistently outperform mixed-tier pairings. Our results indicate that environment tooling and model selection emerge as the strongest drivers of performance, whereas prompt engineering interventions show diminishing or negative returns in well-equipped environments. Reported performance reflects both model reasoning ability and compatibility with agent tooling and API integration.

📄 PDF Abstract BibTeX arXiv:2604.17159

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization

2026-05-24 · Minwei Kong, Chonghe Jiang, Ao Qu, Wenbin Ouyang 외 arxiv

Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a harder capability: designing scalable a…

Computational EfficiencyCode Generation

Benchmarking at the Edge of Comprehension

2026-02-15 · Samuele Marro, Jialin Yu, Emanuele La Malfa, Oishi Deb 외 arxiv

As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard fo…

SO-Bench: A Structural Output Evaluation of Multimodal LLMs

2025-11-23 · Di Feng, Kaixin Ma, Feng Nan, Haofeng Chen 외 arxiv

Multimodal large language models (MLLMs) are increasingly deployed in real-world, agentic settings where outputs must not only be correct, but also conform to predefined data schemas. Despite recent progress in structure…

Information Extraction

Evo-Bench: Can Language Models Improve Agent Harness?

2026-08-10 · Lisheng Huang, Chen Yang, Hao Zhou, Huatong Song 외 hf

Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomou…

Is there "Secret Sauce'' in Large Language Model Development?

2026-02-06 · Matthias Mertens, Natalia Fischl-Lanzoni, Neil Thompson arxiv

Do leading LLM developers possess a proprietary ``secret sauce'', or is LLM performance driven by scaling up compute? Using training and benchmark data for 809 models released between 2022 and 2025, we estimate scaling-l…