LoCoMo

LoCoMo is a benchmark dataset used to evaluate the performance of models in managing and utilizing external memory for long-horizon reasoning tasks.

Papers using LoCoMo (3)

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning2025 · 98 citesDeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory2026