根据查询难易度动态调整智能体协作流程，提升效率与准确率
Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
- 基于难度预测动态生成适配查询的多智能体工作流
- 在6个基准上实现更高准确率与更低推理耗时
- 适合需要高效推理与自适应决策的复杂任务场景
基于大语言模型（LLM）的智能体系统在各类任务中表现出色。然而，现有多智能体框架通常采用静态或任务级工作流，对简单查询过度处理，对复杂查询表现不足，且忽视异构LLM间的效率-性能权衡。为此，我们提出难度感知智能体编排（DAAO），可依据预测的查询难度动态生成查询相关的多智能体工作流。DAAO包含三个相互依赖模块：用于难度估计的变分自编码器（VAE）、模块化操作符分配器，以及兼顾成本与性能的LLM路由器。自适应策略根据工作流成功情况更新难度估计，使简单查询采用简化工序，复杂查询则启用更复杂的策略。在六个基准上的实验表明，DAAO在准确率和推理效率上均优于先前多智能体系统，验证了其在自适应、难度感知推理中的有效性。
原文摘要 · Abstract (English)
Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent frameworks often rely on static or task-level workflows, which either over-process simple queries or underperform on complex ones, while also neglecting the efficiency-performance trade-offs across heterogeneous LLMs. To address these limitations, we propose Difficulty-Aware Agentic Orchestration (DAAO), which can dynamically generate query-specific multi-agent workflows guided by predicted query difficulty. DAAO comprises three interdependent modules: a variational autoencoder (VAE) for difficulty estimation, a modular operator allocator, and a cost- and performance-aware LLM router. A self-adjusting policy updates difficulty estimates based on workflow success, enabling simpler workflows for easy queries and more complex strategies for harder ones. Experiments on six benchmarks demonstrate that DAAO surpasses prior multi-agent systems in both accuracy and inference efficiency, validating its effectiveness for adaptive, difficulty-aware reasoning.
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。