Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning

arXiv:2609.06027 · cs.CR, cs.AI, cs.IR · Submitted 2026-09-05 · Read on arXiv

cs.CR, cs.AI, cs.IR

Submitted: 2026-09-05

Updated: 2026-09-17

Comments: 36 pages, 9 figures, and 10 tables. Code and benchmark: https://github.com/zhonganbi102-netizen/HAE-GEO

Code: https://github.com/zhonganbi102-netizen/HAE-GEO

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Agentic Search — 1× in this paper · explained in 1 episode
• Generative Engine Optimization — 1× in this paper

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs