Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a ''One-for-All'' approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which intergrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we curated a large-scale Chinese instruction-tuning dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY's superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences. Our codes are available at https://github.com/nuochenpku/COMEDY.

翻译：现有基于检索的方法在维持长期对话方面取得了显著进展。然而，这些方法在记忆数据库管理和精准记忆检索方面面临挑战，阻碍了其在动态真实交互中的有效性。本研究提出了一种新颖框架——压缩记忆增强对话系统（COMEDY），该框架摒弃了传统检索模块和记忆数据库。与之相反，COMEDY采用"一统全局"策略，利用单一语言模型管理记忆生成、压缩及响应生成。该框架的核心是压缩记忆概念，它将会话特定摘要、用户-机器人动态及过往事件整合为简洁的记忆格式。为支持COMEDY，我们构建了一个大规模中文指令微调数据集Dolphin，该数据集源自真实用户-聊天机器人交互。对比评估表明，COMEDY在生成更细腻且类人的对话体验方面优于传统基于检索的方法。我们的代码已开源在https://github.com/nuochenpku/COMEDY。