Xuehai Tang

Identifiers

• name variant Xuehai Tang 0.60 · backfill

Papers (4)

1. When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents cs.CR · 2026 · author #2
2. Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills cs.CR · 2026 · author #2
3. RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents cs.CR · 2026 · author #2
4. FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing cs.CL · 2026 · author #3

Mentions

• 2605.24069 #2 · arxiv_oai · confidence 0.70 Xuehai Tang

Frequent Coauthors

• Biyu Zhou 3 shared papers
• Jizhong Han 3 shared papers
• Songlin Hu 3 shared papers
• Wenjie Xiao 2 shared papers
• Jie Wen 1 shared papers
• Liang Lin 1 shared papers
• Lijia Lv 1 shared papers
• Peng Wang 1 shared papers
• Shi Liu 1 shared papers
• Wantao Liu 1 shared papers
• Xikang Yang 1 shared papers