做深度研究智能体或搜索系统的团队，终于有了解决并行搜索证据重复和上下文瓶颈的方案——Argus 用拼图式组装替代暴力搜索，效率提升明显，值得在复杂信息检索任务中尝试。
Argus 提出了一种新的深度研究方法，通过 Searcher 和 Navigator 两个智能体协作，将研究任务视为拼图组装而非暴力并行搜索。Navigator 维护共享证据图，验证缺失信息并调度 Searcher 收集，最终生成带来源追踪的答案。在 35B-A3B MoE 模型上，单 Searcher 提升 5.5 分，8 个并行 Searcher 提升 12.7 分，64 个 Searcher 在 BrowseComp 上达到 86.2，超越所有专有智能体，且 Navigator 推理上下文保持在 21.5K tokens 以内。该方法解决了并行搜索中证据重复和上下文超限的问题。
Argus: Evidence Assembly for Scalable Deep Research Agents
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.