Flash-Searcher：基于DAG并行执行的高效快速网络智能体

摘要

大型语言模型（LLMs）在配备外部工具后，在复杂推理任务中展现了卓越的能力。然而，当前框架主要依赖顺序处理，导致执行效率低下，特别是在需要大量工具交互的任务中。本文提出了Flash-Searcher，一种新颖的并行代理推理框架，从根本上将执行范式从顺序链重新构想为有向无环图（DAGs）。Flash-Searcher将复杂任务分解为具有明确依赖关系的子任务，使得独立推理路径能够并发执行，同时保持逻辑约束。通过动态工作流优化，我们的框架基于中间结果持续优化执行图，有效整合了摘要模块。在多个基准测试中的全面评估表明，Flash-Searcher始终优于现有方法。具体而言，在BrowseComp上达到了67.7%的准确率，在xbench-DeepSearch上达到了83%，同时与当前框架相比，代理执行步骤减少了高达35%。此外，当将此并行推理管道蒸馏为单一模型时，我们观察到在不同骨干架构上显著的性能提升，这凸显了我们方法的通用性。因此，我们的工作代表了代理架构设计的重要进展，为复杂推理任务提供了更具可扩展性和效率的范式。

English

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks when equipped with external tools. However, current frameworks predominantly rely on sequential processing, leading to inefficient execution particularly for tasks requiring extensive tool interaction. This paper introduces Flash-Searcher, a novel parallel agent reasoning framework that fundamentally reimagines the execution paradigm from sequential chains to directed acyclic graphs (DAGs). Flash-Searcher decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths while maintaining logical constraints. Through dynamic workflow optimization, our framework continuously refines the execution graph based on intermediate results, effectively integrating summary module. Comprehensive evaluations across multiple benchmarks demonstrate that Flash-Searcher consistently outperforms existing approaches. Specifically, it achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks. Furthermore, when distilling this parallel reasoning pipeline into single models, we observe substantial performance gains across diverse backbone architectures, underscoring the generalizability of our methodology. Our work thus represents a significant advance in agent architecture design, offering a more scalable and efficient paradigm for complex reasoning tasks.

Flash-Searcher：基于DAG并行执行的高效快速网络智能体

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution

摘要

Support