Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrieval

TL;DR

This paper introduces Wormhole Memory, a novel memory module for large language models that enables cross-dialogue memory sharing through nonlinear indexing and dynamic retrieval, addressing current limitations.

Contribution

The paper presents a new wormhole memory module (WMM) that allows arbitrary retrieval of shared memory across dialogues, improving upon existing memory management methods.

Findings

WMM successfully retrieves memory across dialogues in experiments.

WMM demonstrates stable quantitative performance in multiple tests.

Compared to Titans and MemGPT, WMM offers enhanced cross-dialogue memory retrieval.

Abstract

In view of the gap in the current large language model in sharing memory across dialogues, this research proposes a wormhole memory module (WMM) to realize memory as a Rubik's cube that can be arbitrarily retrieved between different dialogues. Through simulation experiments, the researcher built an experimental framework based on the Python environment and used setting memory barriers to simulate the current situation where memories between LLMs dialogues are difficult to share. The CoQA development data set was imported into the experiment, and the feasibility of its cross-dialogue memory retrieval function was verified for WMM's nonlinear indexing and dynamic retrieval, and a comparative analysis was conducted with the capabilities of Titans and MemGPT memory modules. Experimental results show that WMM demonstrated the ability to retrieve memory across dialogues and the stability of quantitative indicators in eight experiments. It contributes new technical approaches to the optimization of memory management of LLMs and provides experience for the practical application in the future.