SOURCE-LINKED INTELLIGENCE

Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Distributed LLM-agent teams can read the latest shared facts and still act on an obsolete plan. A planner may derive an action from requirement $r_3$, another agent may commit $r_4$, and an executor may receive $r_4$ without replacing the plan derived from $r_3$. We call this \emph{stale-plan execution}: state freshness does not establish that the plan authorizing an action remains valid. We introduce PlanFence, a dependency-scoped action-validation protocol. Plans cite the exact public records they used, and an executor validates only the records that can affect the pending external action, r

Read original source ↗ Open in workspace

recordType

paper

region

Global