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.

翻译：深度研究智能体在跨来源信息整合过程中，严重受限于推理的顺序性。这一瓶颈导致高延迟、运行时适应性差及资源分配低效，使当前深度研究系统难以适用于交互式应用。为此，我们提出ParallelResearch——一种高效深度研究的新型框架，通过将复杂查询动态分解为树状结构子任务，将顺序处理转化为并行运行时编排。核心贡献包含三方面：（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，剪枝冗余路径以重分配资源并支持推测执行；（3）全异步执行基础设施，实现研究广度与深度层面的并发。在两个基准测试上的实验表明，在同等最终报告质量下可实现最高5倍加速，且在相同时间预算内取得持续的质量提升。