让复杂研究任务并行化，动态分配资源，提速5倍且质量不降。
Efficient Tree-Structured Deep Research with Adaptive Resource Allocation
- 将复杂问题拆成树状子任务，动态分配计算资源。
- 运行时剪枝冗余路径，实现推测执行，速度提升5倍。
- 适合需要快速响应的交互式研究场景。
深度研究代理在跨源信息整合时，受限于推理的串行特性，导致延迟高、运行时适应性差、资源分配效率低，难以用于交互式应用。为此，我们提出ParallelResearch框架，将串行处理转化为并行的运行时编排，通过动态分解复杂查询为树状子任务。核心贡献包括：(1) 自适应规划器，根据查询复杂度动态分配计算资源；(2) 运行时编排层，剪枝冗余路径以重新分配资源，并支持推测执行；(3) 完全异步执行基础设施，实现研究广度与深度上的并发。在两个基准测试中，相比现有方法，最多提速5倍，且在相同时间预算下报告质量更优。
原文摘要 · Abstract (English)
Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource allocation, making today's deep research systems impractical for interactive applications. To overcome this, we introduce ParallelResearch, a novel framework for efficient deep research that transforms sequential processing into parallel, runtime orchestration by dynamically decomposing complex queries into tree-structured sub-tasks. Our core contributions are threefold: (1) an adaptive planner that dynamically allocates computational resources based on query complexity; (2) a runtime orchestration layer that prunes redundant paths to reallocate resources and enables speculative execution; and (3) a fully-asynchronous execution infrastructure that enables concurrency across both research breadth and depth. Experiments on two benchmarks show up to 5x speedups with comparable final report quality, and consistent quality improvements with the same time budgets.
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。