提出动态情感记忆管理机制，让AI代理更智能地更新个性化记忆。
Dynamic Affective Memory Management for Personalized LLM Agents
- 用贝叶斯启发的熵减算法自动更新记忆向量库。
- 在情感表达与变化任务上显著提升个性化与逻辑一致性。
- 适合研究长期记忆、个性化AI代理的学者与开发者。
大型语言模型的发展正推动个性化AI代理成为研究热点。当前代理系统主要依赖外部个性化记忆数据库提供定制化体验，但面临记忆冗余、过时及记忆与上下文整合不佳等问题，根源在于交互过程中缺乏有效的记忆更新机制。为此，我们提出一种面向情感场景的记忆管理系统，采用贝叶斯启发的更新算法，引入记忆熵概念，使代理能自主维护动态更新的记忆向量库，通过最小化全局熵实现更个性化的服务。为有效评估系统在该场景下的表现，我们构建了DABench基准，专注于对象的情感表达与情感变化。实验结果表明，该系统在个性化、逻辑连贯性和准确性方面均表现优异。消融实验进一步验证了贝叶斯启发更新机制在缓解记忆膨胀方面的有效性。本工作为长期记忆系统的设计提供了新思路。
原文摘要 · Abstract (English)
Advances in large language models are making personalized AI agents a new research focus. While current agent systems primarily rely on personalized external memory databases to deliver customized experiences, they face challenges such as memory redundancy, memory staleness, and poor memory-context integration, largely due to the lack of effective memory updates during interaction. To tackle these issues, we propose a new memory management system designed for affective scenarios. Our approach employs a Bayesian-inspired memory update algorithm with the concept of memory entropy, enabling the agent to autonomously maintain a dynamically updated memory vector database by minimizing global entropy to provide more personalized services. To better evaluate the system's effectiveness in this context, we propose DABench, a benchmark focusing on emotional expression and emotional change toward objects. Experimental results demonstrate that, our system achieves superior performance in personalization, logical coherence, and accuracy. Ablation studies further validate the effectiveness of the Bayesian-inspired update mechanism in alleviating memory bloat. Our work offers new insights into the design of long-term memory systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。