让大模型更高效地处理复杂对话流程，减少错误和延迟。
Performant LLM Agentic Framework for Conversational AI
- 用数学向量评分辅助大模型选择节点，提升决策准确性。
- 在复杂流程中实现更高准确率，同时降低响应延迟。
- 适合需要实时交互的商业级语音对话系统使用。
随着语音AI行业中智能体应用和自动化的发展，大型语言模型（LLMs）被广泛用于执行基于图结构的逻辑工作流，由节点和边构成。然而，现有方法在复杂工作流中存在对齐错误，且因上下文过长导致幻觉问题。为此，我们提出性能优异的智能体框架（PAF），通过结合大模型推理与数学基础的向量评分机制，协助大模型在遍历复杂图时选择合适节点并有序执行动作。PAF动态平衡预设路径的严格遵循与灵活跳转，有效应对多样用户输入。实验表明，PAF显著优于基线方法，为复杂业务环境中的可扩展、实时对话AI系统铺平道路。
原文摘要 · Abstract (English)
The rise of Agentic applications and automation in the Voice AI industry has led to an increased reliance on Large Language Models (LLMs) to navigate graph-based logic workflows composed of nodes and edges. However, existing methods face challenges such as alignment errors in complex workflows and hallucinations caused by excessive context size. To address these limitations, we introduce the Performant Agentic Framework (PAF), a novel system that assists LLMs in selecting appropriate nodes and executing actions in order when traversing complex graphs. PAF combines LLM-based reasoning with a mathematically grounded vector scoring mechanism, achieving both higher accuracy and reduced latency. Our approach dynamically balances strict adherence to predefined paths with flexible node jumps to handle various user inputs efficiently. Experiments demonstrate that PAF significantly outperforms baseline methods, paving the way for scalable, real-time Conversational AI systems in complex business environments.
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。