On the Structural Memory of LLM Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929641834414080 |
|---|---|
| author | Zeng, Ruihong Fang, Jinyuan Liu, Siwei Meng, Zaiqiao |
| author_facet | Zeng, Ruihong Fang, Jinyuan Liu, Siwei Meng, Zaiqiao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15266 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Structural Memory of LLM Agents Zeng, Ruihong Fang, Jinyuan Liu, Siwei Meng, Zaiqiao Computation and Language Artificial Intelligence 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. |
| title | On the Structural Memory of LLM Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2412.15266 |