{
  "annotation_id": "25155173-6b16-42d0-a82d-c72089770365",
  "date_created": "2026-02-17T05:53:20.058000Z",
  "date_modified": "2026-02-17T05:53:20.058000Z",
  "file_hash": "a8b053c682a3acb8f2e33a8f54444973a3284feb6d18cdea577d40c5b66b3110",
  "private": false,
  "record": {
    "abstract": "Capture-the-Flag (CTF) competitions play a central role in modern cybersecurity as a platform for training practitioners and evaluating offensive and defensive techniques derived from real-world vulnerabilities. Despite recent advances in large language models (LLMs), existing LLM-based agents remain ineffective on high-difficulty cryptographic CTF challenges, which require precise cryptanalytic knowledge, stable long-horizon reasoning, and disciplined interaction with specialized toolchains. Through a systematic exploratory study, we show that insufficient knowledge granularity, rather than model reasoning capacity, is a primary factor limiting successful cryptographic exploitation: coarse or abstracted external knowledge often fails to support correct attack modeling and implementation. Motivated by this observation, we propose KryptoPilot, an open-world knowledge-augmented LLM agent for automated cryptographic exploitation. KryptoPilot integrates dynamic open-world knowledge acquisition via a Deep Research pipeline, a persistent workspace for structured knowledge reuse, and a governance subsystem that stabilizes reasoning through behavioral constraints and cost-aware model routing. This design enables precise knowledge alignment while maintaining efficient reasoning across heterogeneous subtasks. We evaluate KryptoPilot on two established CTF benchmarks and in six real-world CTF competitions. KryptoPilot achieves a complete solve rate on InterCode-CTF, solves between 56 and 60 percent of cryptographic challenges on the NYU-CTF benchmark, and successfully solves 26 out of 33 cryptographic challenges in live competitions, including multiple earliest-solved and uniquely-solved instances. These results demonstrate the necessity of open-world, fine-grained knowledge augmentation and governed reasoning for scaling LLM-based agents to real-world cryptographic exploitation.",
    "arxiv_id": "2601.09129",
    "authors": [
      "Xiaonan Liu",
      "Zhihao Li",
      "Xiao Lan",
      "Hao Ren",
      "Haizhou Wang",
      "Xingshu Chen"
    ],
    "categories": [
      "cs.CR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitation",
    "url": "https://arxiv.org/abs/2601.09129",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "6d021790-2041-4a15-b16c-3cb3d4876651",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}