Score each stored lesson with a Transfer Reliability Score before retrieving it — no fine-tuning, no extra tools

arXiv 2608.12743·medium signalXBlueskyLinkedInCopy link

Spatial Memory Agent improves frozen VLM agents with zero parameter updates: during training it collects experiences in verifiable environments, distills lessons via verifier-guided reflection, and attaches a Transfer Reliability Score (TRS) to each; at inference it retrieves only relevant, reliable lessons. Across five spatial benchmarks and four base VLMs it takes the highest macro average in every base-model block and the best accuracy in most of the 20 evaluations. The generalizable move is the TRS — scoring how well a memory transfers, separate from how well it matches the query, is a memory-design pattern that isn't specific to spatial tasks.