MARS框架让AI agent通过反思和记忆优化，长期任务表现更稳定。
MARS: Memory-Enhanced Agents with Reflective Self-improvement
- 三代理架构+反思机制，动态优化决策过程
- 基于艾宾浩斯遗忘曲线优化记忆，提升长时信息保留
- 适合需要持续学习与多任务处理的智能系统
大型语言模型在自然语言处理领域取得显著进展，但在动态环境中仍面临持续决策、缺乏长期记忆和上下文窗口有限等挑战。为此，本文提出创新性框架Memory-Enhanced Agents with Reflective Self-improvement（MARS）。该框架包含用户、助手与校验者三个代理，通过迭代反馈、反思机制及基于艾宾浩斯遗忘曲线的记忆优化策略，显著提升了代理在多任务和长跨度信息处理中的能力。
原文摘要 · Abstract (English)
Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making, lack of long-term memory, and limited context windows in dynamic environments. To address these issues, this paper proposes an innovative framework Memory-Enhanced Agents with Reflective Self-improvement. The MARS framework comprises three agents: the User, the Assistant, and the Checker. By integrating iterative feedback, reflective mechanisms, and a memory optimization mechanism based on the Ebbinghaus forgetting curve, it significantly enhances the agents capabilities in handling multi-tasking and long-span information.
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。