MemFly：基於資訊瓶頸的即時記憶體優化技術（注：標題採用意譯方式，將"On-the-Fly"譯為「即時」以體現動態特性，"Information Bottleneck"採用學界通用譯法「資訊瓶頸」，整體保持技術論文標題的簡潔性與專業度）

摘要

長期記憶使大型語言模型代理能夠透過歷史互動處理複雜任務。然而現有框架面臨一個根本性困境：既要高效壓縮冗餘信息，又要為下游任務保持精確檢索能力。為解決這一矛盾，我們提出基於信息瓶頸原理的MemFly框架，實現LLM的即時記憶演化機制。該方法通過無梯度優化器最小化壓縮熵的同時最大化相關性熵，構建分層記憶結構以實現高效存儲。為充分發揮MemFly效能，我們開發了融合語義、符號與拓撲路徑的混合檢索機制，結合迭代優化策略處理複雜多跳查詢。綜合實驗表明，MemFly在記憶連貫性、響應保真度與準確性方面顯著超越現有頂尖基準模型。

English

Long-term memory enables large language model agents to tackle complex tasks through historical interactions. However, existing frameworks encounter a fundamental dilemma between compressing redundant information efficiently and maintaining precise retrieval for downstream tasks. To bridge this gap, we propose MemFly, a framework grounded in information bottleneck principles that facilitates on-the-fly memory evolution for LLMs. Our approach minimizes compression entropy while maximizing relevance entropy via a gradient-free optimizer, constructing a stratified memory structure for efficient storage. To fully leverage MemFly, we develop a hybrid retrieval mechanism that seamlessly integrates semantic, symbolic, and topological pathways, incorporating iterative refinement to handle complex multi-hop queries. Comprehensive experiments demonstrate that MemFly substantially outperforms state-of-the-art baselines in memory coherence, response fidelity, and accuracy.

MemFly：基於資訊瓶頸的即時記憶體優化技術（注：標題採用意譯方式，將"On-the-Fly"譯為「即時」以體現動態特性，"Information Bottleneck"採用學界通用譯法「資訊瓶頸」，整體保持技術論文標題的簡潔性與專業度）

MemFly: On-the-Fly Memory Optimization via Information Bottleneck

摘要

Support