MARCO用多智能体实现实时对话自动化，提升任务准确率与效率。
MARCO: Multi-Agent Real-time Chat Orchestration
- 构建多智能体框架，通过约束机制规范LLM行为并自动纠错。
- 在餐饮和零售对话数据集上准确率达94.48%与92.74%，延迟降低44.91%。
- 适合需跨领域、多轮交互的自动化任务场景，设计可复用。
大型语言模型的发展推动了多智能体框架的兴起，用于解决需要与多种工具交互、推理及人类协作的复杂现实问题。我们提出MARCO——一种基于LLM的多智能体实时对话编排框架，用于自动化复杂任务。MARCO解决了LLM在多步任务执行中的关键挑战，引入稳健的约束机制以引导模型行为、验证输出，并从不一致输出格式、函数参数幻觉及领域知识缺失导致的错误中恢复。大量实验表明，MARCO在数字餐厅服务平台对话和零售对话数据集上的任务执行准确率分别达到94.48%和92.74%，同时实现44.91%的延迟降低和33.71%的成本减少。我们还分析了约束机制对性能提升的影响，并对比了开源与专有LLM模型的表现。MARCO模块化且通用的设计使其可适配多个领域，支持通过多轮交互完成复杂任务。
原文摘要 · Abstract (English)
Large language model advancements have enabled the development of multi-agent frameworks to tackle complex, real-world problems such as to automate tasks that require interactions with diverse tools, reasoning, and human collaboration. We present MARCO, a Multi-Agent Real-time Chat Orchestration framework for automating tasks using LLMs. MARCO addresses key challenges in utilizing LLMs for complex, multi-step task execution. It incorporates robust guardrails to steer LLM behavior, validate outputs, and recover from errors that stem from inconsistent output formatting, function and parameter hallucination, and lack of domain knowledge. Through extensive experiments we demonstrate MARCO's superior performance with 94.48% and 92.74% accuracy on task execution for Digital Restaurant Service Platform conversations and Retail conversations datasets respectively along with 44.91% improved latency and 33.71% cost reduction. We also report effects of guardrails in performance gain along with comparisons of various LLM models, both open-source and proprietary. The modular and generic design of MARCO allows it to be adapted for automating tasks across domains and to execute complex usecases through multi-turn interactions.
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。