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

2025-07-31

AI Summary

Large language model (LLM)-based agents face limitations in memory-augmented reasoning due to constrained memory module capacity and difficulty in retrieving vague or incomplete memories. Method: This paper proposes a strategy-guided query generation framework comprising: (1) a structured 5W memory graph and hierarchical retrieval tree to organize abstract memory cues; (2) Monte Carlo Tree Search (MCTS) for dynamic optimization of cue selection strategies; and (3) an LLM-synthesized instruction-tuning dataset, integrating strategy classification, prompt engineering, and reinforcement learning for response generation. Results: The framework achieves a 17.74% average improvement over state-of-the-art methods across three benchmark datasets. Human evaluation confirms its superior capability in eliciting relevant memory cues and enhancing recall completeness in realistic memory-retrieval tasks.

Technology Category

• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Enhancing memory recall using strategy-guided agent queries
• Overcoming limited memory module size in recall systems
• Optimizing recall strategy selection for diverse scenarios

Innovation

• Strategy-guided query transformation for memory recall
• 5W Recall Map classifies queries into scenarios
• Hierarchical recall tree optimizes strategy selection