研究人员开发了Argus，一个新颖的代理系统，旨在通过将证据收集视为拼图组装来改进深度研究能力。与经常重复信息的并行搜索方法不同，Argus采用搜索者（Searcher）和导航者（Navigator）组合。搜索者收集证据痕迹，而导航者管理证据图，识别缺失的部分，并综合最终答案。这种方法在基准测试中显著提高了性能，64个搜索者在BrowseComp上取得了86.2的成绩，在保持可管理的上下文窗口的同时，性能优于专有代理。 AI
影响 Argus展示了一种新颖的AI代理证据组装方法，有望提高复杂研究任务的效率和性能。
排序理由 该集群包含一篇详细介绍新型研究代理系统的arXiv论文。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2605.24218v1 Announce Type: new Abstract: Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while…
arXiv:2605.16217v3 Announce Type: replace-cross Abstract: 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 compu…
QUEST is an open-family of deep research agents trained with synthesized data and reinforcement learning to perform well across diverse long-horizon search tasks.
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 …