The latest advancements in AI and deep learning have led to a breakthrough in large language model (LLM)-based agents such as GPT-4. However, many commercial conversational agent development tools are pipeline-based and have limitations in holding a human-like conversation. This paper investigates the capabilities of LLMs to enhance pipeline-based conversational agents during two phases: 1) in the design and development phase and 2) during operations. In 1) LLMs can aid in generating training data, extracting entities and synonyms, localization, and persona design. In 2) LLMs can assist in contextualization, intent classification to prevent conversational breakdown and handle out-of-scope questions, auto-correcting utterances, rephrasing responses, formulating disambiguation questions, summarization, and enabling closed question-answering capabilities. We conducted informal experiments with GPT-4 in the private banking domain to demonstrate the scenarios above with a practical example. Companies may be hesitant to replace their pipeline-based agents with LLMs entirely due to privacy concerns and the need for deep integration within their existing ecosystems. A hybrid approach in which LLMs' are integrated into the pipeline-based agents allows them to save time and costs of building and running agents by capitalizing on the capabilities of LLMs while retaining the integration and privacy safeguards of their existing systems.

翻译：人工智能和深度学习的最新进展带来了基于大型语言模型（LLM）的智能体（如GPT-4）的突破性发展。然而，许多商业对话代理开发工具仍基于流水线架构，在实现拟人化对话方面存在局限性。本文研究了LLM在两个阶段增强流水线对话代理的能力：1）设计与开发阶段；2）运营阶段。在阶段1）中，LLM可辅助生成训练数据、提取实体与同义词、实现本地化及人格设计。在阶段2）中，LLM可协助上下文理解、意图分类以预防对话中断并处理领域外问题、自动纠错话语、改写回复、制定消歧问题、执行摘要生成，并实现封闭域问答能力。我们以私有银行领域为例，通过非正式实验展示了上述应用场景。由于隐私保护需求及与现有生态系统的深度集成要求，企业可能不愿完全用LLM替换现有流水线代理。将LLM集成至流水线代理的混合方法，既能利用LLM的能力节省构建和运行代理的时间与成本，又能保留现有系统的集成性与隐私保护机制。