This paper introduces RAISE (Reasoning and Acting through Scratchpad and Examples), an advanced architecture enhancing the integration of Large Language Models (LLMs) like GPT-4 into conversational agents. RAISE, an enhancement of the ReAct framework, incorporates a dual-component memory system, mirroring human short-term and long-term memory, to maintain context and continuity in conversations. It entails a comprehensive agent construction scenario, including phases like Conversation Selection, Scene Extraction, CoT Completion, and Scene Augmentation, leading to the LLMs Training phase. This approach appears to enhance agent controllability and adaptability in complex, multi-turn dialogues. Our preliminary evaluations in a real estate sales context suggest that RAISE has some advantages over traditional agents, indicating its potential for broader applications. This work contributes to the AI field by providing a robust framework for developing more context-aware and versatile conversational agents.

翻译：本文提出了RAISE（通过暂存器与示例进行推理与行动）架构，这是一种增强大语言模型（如GPT-4）与对话智能体集成能力的高级架构。作为ReAct框架的改进方案，RAISE通过模拟人类短期与长期记忆的双组件记忆系统，实现了对话上下文与连续性的保持。该架构包含完整的智能体构建流程，涵盖对话筛选、场景提取、思维链补全及场景增强等阶段，最终进入大语言模型训练阶段。该方案在多轮复杂对话中展现出增强的智能体可控性与适应性。我们基于房地产销售场景的初步评估表明，RAISE较传统智能体具有显著优势，预示其具有广泛的应用潜力。本研究通过构建更具语境感知能力和多场景适应性的对话智能体框架，为人工智能领域做出了贡献。