arXiv CS AI
techLean Right
When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agentstranslating…
arXiv:2609.05441v1 Announce Type: new
Abstract: Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dialogue history, not whether remembered facts change what a tool-using agent…
Keywords#Memory#LLM Agents#Long-Term Memory#Tool-Using#A Cost-Aware