工业运维对话系统提升多轮交互效率，减少工具重复调用。
Towards Multi-Turn Dialog Systems for Industrial Asset Operations and Maintenance
- 采用总管-专家多智能体架构支持多轮协作
- 任务完成率提升37.8%，规划效率提高54.5%
- 适合需要复杂工具调用的工业场景应用
工业资产运维问答本质上是多轮、迭代且高度依赖外部工具调用的过程。传统单一智能体的计划-执行架构在跨轮次上下文保持和中间结果复用方面存在明显局限。本文提出一种基于总管-专家多智能体架构的工业场景多轮对话系统。为缓解工具调用瓶颈，系统引入结构化成果复用、动态重规划与并行工具执行机制。评估结果显示，相比基线系统，本系统响应质量更优，规划有效性提升54.5%，任务完成率提高37.8%。系统分析表明，跨轮次成果复用有效减少冗余工具调用，工具使用时间占比从47.3%降至26.3%，第2至第5轮平均速度比第一轮快约4.2倍。
原文摘要 · Abstract (English)
Industrial asset operations and maintenance question answering is inherently multi-turn, iterative, and highly dependent on external tool invocation. However, the conventional plan-execute single-agent architecture exhibits clear limitations in maintaining cross-turn context, and reusing intermediate results. In this paper, we present a multi-turn dialog system designed for industrial scenarios based on a supervisor-specialist multi-agent architecture. To alleviate tool invocation bottlenecks, the system incorporates structured artifact reuse, dynamic replanning, and parallel tool execution. Evaluation results show that our system achieves better response quality compared with the baseline, with planning effectiveness increasing by 54.5% and task completion improving by 37.8%. System profiling further shows that cross-turn artifact reuse effectively reduces redundant tool invocation, decreasing the tool-time share from 47.3% to 26.3% and making turns 2-5 approximately 4.2x faster than the first turn.
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。