arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.03841cs.SEcs.AI
收藏

MaxMind:一种基于大语言模型提升软件生产力的记忆循环网络

MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Models

National University of Defence Technology(国防科技大学);School of Computer(计算机学院);Southeast University(东南大学);School of Integrated Circuits(集成电路学院)

Yuchen Dong, XiaoXiang Fang, Yuchen Hu, Renshuang Jiang, Zhe Jiang

AI总结:

本文提出记忆循环网络MaxMind,通过经验记忆、价值区分和知识精确分割增强RAG,并在电子表格系统中验证其可提升任务成功率与执行效率。

摘要:

将大语言模型用于促进自动化软件操作与工具生成(SOTG),从而提升软件生产力,类似于人类进化的早期阶段,当时创造和使用工具的能力加速了文明进程。这些复杂任务要求AI不断总结和改进。当前研究往往忽视了将实时任务经验转化为系统记忆,并区分现有知识对未来参考的价值的重要性。本文通过将外部记忆模型演进为用于及时记忆和经验参考的记忆循环网络来解决这些问题。我们还通过知识精确分割增强RAG机制,以基于价值区分利用记忆,并相应地为SOTG设计了MaxMind模型。为展示我们的方法,我们开发了MaxMind4Sheet,这是一个符合MaxMind理念的电子表格处理系统。与SheetCopilot的对比实验表明,任务记忆的积累和循环利用使任务成功率稳步提升,在该实现示例中每轮提升率约为3%-6%。需要注意的是,随着记忆持续增长,这种累积提升可能相当可观。引入记忆循环还可将系统的任务执行效率提高至多25%,并能通过记忆迁移解决LLM在处理专业任务时面临的再训练问题。这些结果表明,MaxMind在增强LLM系统在SOTG中的能力和生产力方面具有巨大潜力。

英文摘要:

The application of large language models to facilitate automated software operations and tool generation (SOTG), thus augmenting software productivity, mirrors the early stages of human evolution when the ability to create and use tools accelerated the progress of civilization. These complex tasks require AI to continuously summarize and improve. Current research often overlooks the importance of converting real-time task experiences into system memory and differentiating the value of existing knowledge for future reference. This paper addresses these issues by evolving external memory models into Memory-Loop Networks for timely memorization and experience referencing. We also enhance a RAG mechanism with knowledge precision segmentation to utilize memory based on value differentiation, and design the MaxMind model for SOTG accordingly.To demonstrate our approach, we developed MaxMind4Sheet, an electronic spreadsheet processing system aligned with the MaxMind philosophy. Comparative experiments with SheetCopilot have demonstrated that the accumulation and recycling of task memories lead to a steady enhancement in task success rate, with an improvement rate of approximately 3%-6% per round in this implementation example. Note that as the memories continue to grow, this cumulative improvement may be substantial. The inclusion of memory recycling can also boost the system's task execution efficiency by up to 25%, and it can address the retraining issue faced by LLMs when handling specialized tasks through memories transfer.These suggest that MaxMind has significant potential to enhance the capabilities and productivity of LLM systems in SOTG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑