Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of the art systems scale inference time compute via parallel search and aggregation. Yet deep research answers are composed of complementary pieces of evidence, which parallel rollouts often duplicate rather than complete, yielding diminishing returns while pushing the aggregation context toward the model's limit. We propose Argus, an agentic system in which a Searcher and a Navigator cooperate to treat deep research as assembling a jigsaw from complementary evidence pieces, rather than brute forcing the whole answer in parallel. The Searcher collects evidence traces for a given sub-query through ReAct-style interaction. The Navigator maintains a shared evidence graph, verifying which pieces are still missing, dispatching Searchers to gather them, and reasoning over the completed graph to produce a source-traced final answer. We train the Navigator with reinforcement learning to verify, dispatch, and synthesize, while independently training the Searcher to remain a standard ReAct agent. The resulting Navigator supports rollouts with a single Searcher or many in parallel without retraining. With both Searcher and Navigator built on a 35B-A3B MoE backbone, Argus gains 5.5 points with a single Searcher and 12.7 points with 8 parallel Searchers, averaged over eight benchmarks. With 64 Searchers it reaches 86.2 on BrowseComp, surpassing every proprietary agent we benchmark, while the Navigator's reasoning context stays under 21.5K tokens.

翻译：深度研究代理在复杂信息检索任务上取得了显著进展。即便采用长链式ReAct交互范式，其探索轨迹仍局限于单一路径，而当前最先进的系统通过并行搜索与聚合来扩展推理时计算。然而深度研究答案需由互补性证据片段组成，并行轨迹往往产生重复而非完整的证据，导致边际效益递减并促使聚合上下文逼近模型极限。我们提出Argus系统，通过"搜索器"与"导航器"的协同机制，将深度研究重构为从互补证据碎片中拼合拼图的过程，而非对整答案进行暴力并行求解。搜索器通过ReAct交互为给定子查询收集证据痕迹；导航器维护共享证据图谱，验证缺失证据片段，调度搜索器进行获取，并对完整图谱进行推理以生成带来源追踪的最终答案。我们采用强化学习训练导航器，使其具备验证、调度与综合能力，同时独立训练搜索器保持标准ReAct代理形态。由此产生的导航器无需重新训练即可支持单搜索器或多搜索器（并行）的交互流程。基于35B-A3B MoE骨干网络构建的搜索器与导航器，在八个基准测试上，单搜索器配置下性能提升5.5个点，8个并行搜索器配置下提升12.7个点。当采用64个搜索器时，在BrowseComp基准上达到86.2分，超越所有我们测试的专有代理，同时导航器的推理上下文保持在21.5K词元以内。