paperMay 2026Unreviewed

Towards Security-Auditable LLM Agents: A Unified Graph Representation

Chaofan Li, Lyuye Zhang, Jintao Zhai, Siyue Feng, Xichun Yang, Huahao Wang, Shihan Dou, Yu Ji, Yutao Hu, Yueming Wu, Yang Liu, Deqing Zou

View resource PDF

Abstract

LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a severe semantic gap between low-level physical events and high-level execution intent, making post-hoc security auditing fundamentally difficult. Existing representation mechanisms, including static SBOMs and runtime logs, provide only fragmented evidence and fail

Cite

@misc{li2026securityauditable,
  title = {{Towards Security-Auditable LLM Agents: A Unified Graph Representation}},
  author = {Chaofan Li and Lyuye Zhang and Jintao Zhai and Siyue Feng and Xichun Yang and Huahao Wang and Shihan Dou and Yu Ji and Yutao Hu and Yueming Wu and Yang Liu and Deqing Zou},
  year = {2026},
  month = may,
  eprint = {2605.06812},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.06812}
}