SOURCE-LINKED INTELLIGENCE

Facts Without Rules: Boundary Metadata Collapse in Multi-Agent LLM Handoffs

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Multi-agent LLM systems often coordinate by compressing an upstream interaction into a handoff artifact that downstream agents treat as shared state. We show that this handoff step is a structural source of privacy leakage: summaries preferentially preserve operational facts while weakening the boundary metadata that governs how those facts may be used---a failure mode we call \emph{summary collapse}. On a controlled multi-agent coordination testbed we measure marker survival with a human-validated judge ($κ= 0.74$), where $σ_b = 1$ means every boundary marker survives verbatim and $σ_b = 0$ m

Read original source ↗ Open in workspace

recordType

paper

region

Global