Author

Guang-Dong Bai

h-index 8 View on Semantic Scholar

We have 3 of 22 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Review Oct 2026

Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition

Agent skills extend the capabilities of AI agents by bundling instructions, code, and resources into reusable packages. During skill execution, agents may produce or modify artifacts, such as files, configurations, and cached data, that are reused by other skills in later sessions. Since these artifacts can persist acr...

Dian-Shu Liao, Shi-Dong Pan, Guang-Dong Bai et al. · 0 citations

Preprint Sep 2026

Continuous Assurance of Agentic Security Auditors for Software Delivery Decision Gates

This work proposes the Policy-Evidence-Execution Separation Pattern, implemented by the Trustworthy AI Posture (TAIP) Assurance Engine and operated as Continuous Control Posture Assurance (CCPA) and is evaluated across increasing numbers of independent Decision Gateway contexts.

Guy Lupo, Nguyen Hung Nguyen, V. Vo et al. · 0 citations

Jul 2026

A Comprehensive Study of Implementation Bugs in Multi-modal Agents

This work provides a comprehensive reference and guideline for classification, prevention and fix of M-agent bugs, and developed a comprehensive taxonomy that classifies bugs by global symptoms, functionality component-level symptoms, and root causes.

Suwan Li, Lei Bu, Shangqing Liu et al. · arXiv.org · 0 citations