工具集成大型语言模型的最新进展使网络搜索成为信息查找代理的核心能力。然而, 随着交互历史的增长, 代理越来越难以跟踪任务进度。当搜索尝试未能产生有用的证据时，, 当前的单代理和多代理系统可能会陷入重复循环, 浪费搜索预算，并最终损害最终输出的质量和完整性。我们引入 SearchOS, 一个系统级多代理框架，它将脆弱的, 隐式搜索进度转变为显式, 持久, 和共享状态。首先,，我们将开放域信息搜索制定为具有接地引用, 的关系模式完成，其中代理发现实体, 在链接表, 中填充属性，并将每个值锚定到源证据。然后我们设计面向搜索的上下文管理(SOCM),，它将不断发展的状态具体化为前沿任务,、证据图,、覆盖图, 和故障记忆。基于 SOCM, SearchOS 构建，采用管道并行调度机制，该机制与子代理的执行重叠，并不断用针对未解决的覆盖间隙的任务重新填充空闲槽，以提高利用率和吞吐量。为了安排和控制搜索代理的执行, SearchOS 引入了搜索工具中间件线束，该工具可拦截模型和工具交互，以记录有根据的证据并对停滞或预算耗尽做出反应,，并提供可重用的分层技能系统，其中包括策略和访问技能，以增强代理 搜索过程并避免在运行中重复失败的搜索模式。在 WideSearch 和 GISA, 上，SearchOS 在评估的单代理和多代理基线中的所有指标均领先,，为稳健的信息寻求协作铺平了道路。
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.
科目: 人工智能 (cs.AI); 信息检索 (cs.IR)
Subjects: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)