SOURCE-LINKED INTELLIGENCE
Closed-World Resolution Against Tool Hallucination in LLM Agents
Tool-augmented large language model (LLM) agents fail in a way no tool-selection or tool-security method addresses: they call tools that do not exist and pass arguments no schema declares. Existing defenses either pick the right tool (selection) or constrain what an agent may do with real tools (gating), both of which presuppose the emitted call refers to a real tool at all. We show this is a structural blind spot: a hallucinated call is by construction not a decision any gate made, so no gate can reject it. This paper is primarily a measurement and benchmark study. We give a five-class taxono
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · Artificial Intelligence · 2026-09-16T21:02:31.000Z
- arXiv · AI, language, vision and robotics · 2026-09-16T21:02:31.000Z
First collected: 2026-09-19T20:26:32.566Z. This is not the publication date.