SearchOS-V1：邁向穩健的開放領域資訊搜尋智能體協作

SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

July 16, 2026

作者: Yuyao Zhang, Junjie Gao, Zhengxian Wu, Jiaming Fan, Jin Zhang, Shihan Ma, Yao Yao, Weiran Qi, Chuyan Jin, Guiyu Ma, Xingzhong Xu, Kai Yang, Ji-Rong Wen, Zhicheng Dou

cs.AI

摘要

工具整合大型語言模型的最新進展，使網頁搜尋成為資訊搜尋代理的核心能力。然而，隨著互動歷史的增長，代理追蹤任務進度的難度也隨之增加。當搜尋嘗試未能取得有用證據時，現有的單一代理與多代理系統可能陷入重複迴圈，浪費搜尋預算，最終損害最終輸出的品質與完整性。我們提出SearchOS——一個系統層級的多代理框架，將脆弱且隱含的搜尋進度轉化為明確、持久且共享的狀態。首先，我們將開放式資訊搜尋形式化為帶有基礎引用的關聯式綱要補全任務，代理在其中發現實體、在連結表格中填入屬性，並將每個值錨定於來源證據。接著，我們設計了搜尋導向上下文管理（SOCM），將演化中的狀態外部化為前緣任務、證據圖、覆蓋圖與失敗記憶。基於SOCM，SearchOS應用了一種管線並行排程機制，該機制重疊執行子代理，並持續以針對未解決覆蓋缺口之任務填補釋出的空槽，以提升利用率與吞吐量。為排程與控制搜尋代理的執行，SearchOS引入了搜尋工具中介層集線器，攔截模型與工具的互動以記錄基礎證據，並在停滯或預算耗盡時做出反應；此外，還提供一套可重用的層級化技能系統，包含策略技能與存取技能，以增強代理的搜尋流程，並避免在多次運行中重複失敗的搜尋模式。在WideSearch與GISA上，SearchOS在所有評估的單一代理與多代理基線中領先所有指標，為穩健的資訊搜尋協作鋪平道路。

English

Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final output. We introduce SearchOS, a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state. First, we formulate open-domain information seeking as relational schema completion with grounded citations, where agents discover entities, populate attributes across linked tables, and anchor each value to source evidence. Then we design Search-Oriented Context Management (SOCM), which externalizes the evolving state into Frontier Task, an Evidence Graph, a Coverage Map, and Failure Memory. Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents and continuously refills freed slots with tasks targeting unresolved coverage gaps to improve utilization and throughput. To schedule and control the execution of search agents, SearchOS introduces a Search Tool Middleware Harness that intercepts model and tool interactions to record grounded evidence and react to stalls or budget exhaustion, and provides a reusable hierarchical skill system comprising strategy and access skills to augment the agents' search process and avoid repeating failed search patterns across runs. On WideSearch and GISA, SearchOS leads all metrics among the evaluated single- and multi-agent baselines, paving the way toward robust information-seeking collaboration.