Skip to content

Source paper

SimpleMem: Efficient Lifelong Memory for LLM Agents

Jiaqi Liu, Yaofeng Su, Peng Xia and 5 more

Jiaqi Liu, Yaofeng Su, Peng Xia, Siwei Han, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao

arXiv 2601.02553 · 202617 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

This paper introduces SimpleMem, a memory framework for LLM agents designed to balance long-term reasoning accuracy with token efficiency. The system replaces raw context retention with a pipeline that actively compresses dialogue into atomic facts, recursively consolidates them into abstract summaries, and dynamically adjusts retrieval scope based on query complexity.

How it works (AI summary)

The model uses a three-stage pipeline: (1) Semantic Structured Compression, which uses entropy-aware filtering and coreference/temporal normalization to create standalone memory units; (2) Recursive Memory Consolidation, an asynchronous process that clusters memories based on semantic and temporal affinity to form higher-level abstractions; and (3) Adaptive Query-Aware Retrieval, which classifies query complexity to toggle between retrieving high-level summaries or detailed factual records.