SOURCE-LINKED INTELLIGENCE

ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic boundaries enable precise retrieval and direct comparison between observations. Yet accumulating atoms inevitably become redundant, overlapping, or conflicting. Existing methods often ask an LLM manager to add, update, delete, or rewrite memories directly, coupling semantic interpretation, storage decisions, and content generation in one error-prone operation. We introduce ROAM, a relation-guided framework that uses atomicity for management while all

Read original source ↗ Open in workspace

recordType

paper

region

Global