Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
This work addresses memory management for LLM agents in long-term interaction and personalization, offering a novel approach to overcome limitations in existing summary-based methods, though it is incremental in improving extraction processes.
The paper tackles the problem of incomplete and error-prone memory extraction in LLM agents by proposing ProMem, an iterative cognitive process with a recurrent feedback loop that uses self-questioning to probe dialogue history, resulting in improved memory completeness and QA accuracy with a better trade-off between extraction quality and token cost.
Memory management is vital for LLM agents to handle long-term interaction and personalization. Most research focuses on how to organize and use memory summary, but often overlooks the initial memory extraction stage. In this paper, we argue that existing summary-based methods have two major limitations based on the recurrent processing theory. First, summarization is "ahead-of-time", acting as a blind "feed-forward" process that misses important details because it doesn't know future tasks. Second, extraction is usually "one-off", lacking a feedback loop to verify facts, which leads to the accumulation of information loss. To address these issues, we propose proactive memory extraction (namely ProMem). Unlike static summarization, ProMem treats extraction as an iterative cognitive process. We introduce a recurrent feedback loop where the agent uses self-questioning to actively probe the dialogue history. This mechanism allows the agent to recover missing information and correct errors. Our ProMem significantly improves the completeness of the extracted memory and QA accuracy. It also achieves a superior trade-off between extraction quality and token cost.