SOURCE-LINKED INTELLIGENCE

MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over its response. Yet this capability has remained largely overlooked. To assess this capability, we introduce MemCalib, a benchmark grounded in realistic memory-system scenarios for evaluating memory use and advancing optimization algorithms. Results on the MemCalib test set reveal that frontier open- and closed-source models struggle to use memory appropriately. They frequently over-use or under-use memory rather than matching each proposition's

Read original source ↗ Open in workspace

recordType

paper

region

Global