Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies
To address this challenge, we propose a memory multi-class dataset in this paper, termed TriMEM, which provides precise annotations for memory types across diverse scenarios.
Key points
- The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently.
- Thus, an intuitive question arises: can we categorize memory into different types and select appropriate strategies?
- Building upon this foundation, we propose a novel memory framework, named MemoType, which can adaptively recognize each memory and query type with the learned router model.
- Moreover, we theoretically prove that any single retrieval strategy is subject to a fundamental upper bound on its expected retrieval precision in multi-class corpora, leading to systematic precision degradation.
Sources (1)
- [1]Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse StrategiesarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 09:28 AM
To address this challenge, we propose a memory multi-class dataset in this paper, termed TriMEM, which provides precise annotations for memory types across diverse scenarios.
The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently.
Extractive summary: sentences quoted from the sources.