CLAIDec 17, 2024

On the Structural Memory of LLM Agents

arXiv:2412.15266v126 citationsh-index: 12
Originality Incremental advance
AI Analysis

This work addresses the problem of optimizing memory systems for LLM agents in tasks like QA and dialogue, but it is incremental as it builds on existing memory modules.

This paper investigates how different memory structures and retrieval methods affect the performance of LLM-based agents across tasks, finding that mixed memory structures are resilient in noisy environments and iterative retrieval consistently outperforms other methods.

Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these tasks, the impact of different memory structures across tasks remains insufficiently explored. This paper investigates how memory structures and memory retrieval methods affect the performance of LLM-based agents. Specifically, we evaluate four types of memory structures, including chunks, knowledge triples, atomic facts, and summaries, along with mixed memory that combines these components. In addition, we evaluate three widely used memory retrieval methods: single-step retrieval, reranking, and iterative retrieval. Extensive experiments conducted across four tasks and six datasets yield the following key insights: (1) Different memory structures offer distinct advantages, enabling them to be tailored to specific tasks; (2) Mixed memory structures demonstrate remarkable resilience in noisy environments; (3) Iterative retrieval consistently outperforms other methods across various scenarios. Our investigation aims to inspire further research into the design of memory systems for LLM-based agents.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes