MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying

TL;DR

MemoCue is a novel LLM-based agent that enhances human memory recall by strategically transforming queries into cue-rich prompts, addressing memory size limitations and improving recall effectiveness through a hierarchical strategy selection framework.

Contribution

The paper introduces MemoCue, a strategy-guided approach with a Recall Router framework and Monte Carlo Tree Search to optimize memory recall strategies in LLM agents, a novel method in this domain.

Findings

MemoCue outperforms existing LLM-based methods by 17.74% in recall inspiration.

The hierarchical recall tree effectively selects recall strategies across diverse scenarios.

Human evaluations confirm MemoCue's advantages in memory-recall tasks.

Abstract

Agent-assisted memory recall is one critical research problem in the field of human-computer interaction. In conventional methods, the agent can retrieve information from its equipped memory module to help the person recall incomplete or vague memories. The limited size of memory module hinders the acquisition of complete memories and impacts the memory recall performance in practice. Memory theories suggest that the person's relevant memory can be proactively activated through some effective cues. Inspired by this, we propose a novel strategy-guided agent-assisted memory recall method, allowing the agent to transform an original query into a cue-rich one via the judiciously designed strategy to help the person recall memories. To this end, there are two key challenges. (1) How to choose the appropriate recall strategy for diverse forgetting scenarios with distinct memory-recall characteristics? (2) How to obtain the high-quality responses leveraging recall strategies, given only abstract and sparsely annotated strategy patterns? To address the challenges, we propose a Recall Router framework. Specifically, we design a 5W Recall Map to classify memory queries into five typical scenarios and define fifteen recall strategy patterns across the corresponding scenarios. We then propose a hierarchical recall tree combined with the Monte Carlo Tree Search algorithm to optimize the selection of strategy and the generation of strategy responses. We construct an instruction tuning dataset and fine-tune multiple open-source large language models (LLMs) to develop MemoCue, an agent that excels in providing memory-inspired responses. Experiments on three representative datasets show that MemoCue surpasses LLM-based methods by 17.74% in recall inspiration. Further human evaluation highlights its advantages in memory-recall applications.