Preprint · 2026 · Open access

AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents

Yixi Lin, Jiangrong Wu, Yuhong Nan, Xueqiang Wang, Xinyuan Zhang, Zibin Zheng

arXiv (Cornell University) · Published 8 March 2026 · DOI 10.48550/arxiv.2603.07557

Open PDFView at the publisherCite this paper

In brief

“AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents” is a 2026 preprint by Yixi Lin and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 6 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
6
Most cited in
2026 (6)
References
42
Authors
6

Abstract

The rapid integration of Large Language Model (LLM) agents into autonomous task execution has introduced significant privacy concerns within cross-tool data flows. In this paper, we systematically investigate and define a novel risk termed Data Over-Exposure (DOE) in LLM Agent, where an Agent inadvertently transmits sensitive data beyond the scope of user intent and functional necessity. We identify that DOE is primarily driven by the broad data paradigms in tool design and the coarse-grained data processing inherent in LLMs. In this paper, we present AgentRaft, the first automated framework for detecting DOE risks in LLM agents. AgentRaft combines program analysis with semantic reasoning through three synergistic modules: (1) it constructs a Cross-Tool Function Call Graph (FCG) to model the interaction landscape of heterogeneous tools; (2) it traverses the FCG to synthesize high-quality testing user prompts that act as deterministic triggers for deep-layer tool execution; and (3) it performs runtime taint tracking and employs a multi-LLM voting committee grounded in global privacy regulations (e.g., GDPR, CCPA, PIPL) to accurately identify privacy violations. We evaluate AgentRaft on a testing environment of 6,675 real-world agent tools. Our findings reveal that DOE is indeed a systemic risk, prevalent in 57.07% of potential tool interaction paths. AgentRaft achieves a high detection accuracy and effectiveness, outperforming baselines by 87.24%. Furthermore, AgentRaft reaches near-total DOE coverage (99%) within only 150 prompts while reducing per-chain verification costs by 88.6%. Our work provides a practical foundation for building auditable and privacy-compliant LLM agent systems.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Lin, Y., Wu, J., Nan, Y., Wang, X., Zhang, X., & Zheng, Z. (2026). AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.07557

MLA 9

Lin, Yixi, et al. “AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.07557.

Chicago

Lin, Yixi, Jiangrong Wu, Yuhong Nan, Xueqiang Wang, Xinyuan Zhang, and Zibin Zheng. 2026. “AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.07557.

Harvard

Lin, Y. et al. (2026) ‘AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2603.07557.

IEEE

Y. Lin, J. Wu, Y. Nan, X. Wang, X. Zhang, and Z. Zheng, “AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.07557.

BibTeX

@misc{lin2026agentraft,
  title     = {{AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents}},
  author    = {Lin, Yixi and Wu, Jiangrong and Nan, Yuhong and Wang, Xueqiang and Zhang, Xinyuan and Zheng, Zibin},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2603.07557},
  url       = {https://doi.org/10.48550/arxiv.2603.07557}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • LLM agents
  • privacy violations
  • privacy compliance
  • sensitive data leakage
  • tool interaction

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Lin, Y., Wu, J., Nan, Y., Wang, X., Zhang, X., & Zheng, Z. (2026). AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.07557

How many times has this paper been cited?

6 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yixi Lin, Jiangrong Wu, Yuhong Nan, Xueqiang Wang, Xinyuan Zhang, Zibin Zheng.

What is the DOI of this paper?

10.48550/arxiv.2603.07557, permanently at https://doi.org/10.48550/arxiv.2603.07557. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.