Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information seeking. However, when confronted with wide search tasks characterized by large-scale, breadth-oriented retrieval, existing agentic frameworks, primarily designed around sequential, vertically structured reasoning, remain stuck in expansive search objectives and inefficient long-horizon execution. To bridge this gap, we propose A-MapReduce, a MapReduce paradigm-inspired multi-agent execution framework that recasts wide search as a horizontally structured retrieval problem. Concretely, A-MapReduce implements parallel processing of massive retrieval targets through task-adaptive decomposition and structured result aggregation. Meanwhile, it leverages experiential memory to drive the continual evolution of query-conditioned task allocation and recomposition, enabling progressive improvement in large-scale wide-search regimes. Extensive experiments on five agentic benchmarks demonstrate that A-MapReduce is (i) high-performing, achieving state-of-the-art performance on WideSearch and DeepWideSearch, and delivering 5.11% - 17.50% average Item F1 improvements compared with strong baselines with OpenAI o3 or Gemini 2.5 Pro backbones; (ii) cost-effective and efficient, delivering superior cost-performance trade-offs and reducing running time by 45.8\% compared to representative multi-agent baselines. The code is available at https://github.com/mingju-c/AMapReduce.

翻译：当代基于大语言模型的多智能体系统在深度研究任务中展现出系统性优势，这类任务强调迭代式、垂直结构化的信息探寻。然而，当面对以大规模、面向广度的检索为特征的广度搜索任务时，现有主要围绕顺序化、垂直结构化推理设计的智能体框架，仍受限于宽泛的搜索目标与低效的长程执行。为弥合这一差距，我们提出了A-MapReduce，一个受MapReduce范式启发的多智能体执行框架，它将广度搜索重新构建为一个水平结构化的检索问题。具体而言，A-MapReduce通过任务自适应分解与结构化结果聚合，实现了对海量检索目标的并行处理。同时，它利用经验记忆驱动查询条件化任务分配与重组的持续演进，从而在大规模广度搜索场景中实现渐进式改进。在五个智能体基准测试上的广泛实验表明，A-MapReduce具有以下特点：（i）高性能，在WideSearch和DeepWideSearch上达到了最先进的性能，与使用OpenAI o3或Gemini 2.5 Pro作为骨干网络的强基线相比，平均Item F1分数提升了5.11%至17.50%；（ii）成本效益高且高效，与代表性的多智能体基线相比，提供了更优的性价比权衡，并将运行时间减少了45.8%。代码可在 https://github.com/mingju-c/AMapReduce 获取。