SwiftMem: Towards Lightweight and Efficient Memory for LLM Agents

Tool-based memory systems enable agents to autonomously manage long-term memories, but may introduce substantial token overhead through unnecessary retrieval and excessive memory returns. We propose SwiftMem, a lightweight and token-efficient memory system that uses plain text files and three simple memory tools. SwiftMem introduces memory probing to guide retrieval decisions, tag-based query enhancement to improve retrieval quality, and Adaptive Memory Subset Selection to balance retrieval utility and cost. Experiments on two benchmarks show that SwiftMem achieves superior memory performance while substantially reducing token consumption compared with existing tool-based memory systems (up to 1/2). We provide the source code of SwiftMem in https://anonymous.4open.science/r/SwiftMem.