SearchOS-V1: 面向鲁棒开放域信息搜寻的智能体协作

摘要

工具集成大语言模型的最新进展使得网络搜索成为信息获取型智能体的核心能力。然而，随着交互历史的增长，智能体越来越难以追踪任务进度。当搜索尝试未能获得有价值的证据时，现有的单智能体和多智能体系统容易陷入重复循环，浪费搜索预算，最终影响最终输出的质量和完整性。我们提出SearchOS——一种系统级多智能体框架，将脆弱且隐式的搜索进度转化为显式、持久且共享的状态。首先，我们将开放域信息获取形式化为带有引文的关系模式补全，其中智能体发现实体、填充跨链接表的属性，并将每个值锚定到源证据。然后，我们设计了搜索导向型上下文管理（SOCM），将演化中的状态外化为前沿任务、证据图、覆盖图和失败记忆。基于SOCM，SearchOS采用流水线并行调度机制，该机制重叠执行子智能体，并持续用针对未解析覆盖缺口任务填充空出的槽位，从而提高利用率和吞吐量。为了调度和控制搜索智能体的执行，SearchOS引入了搜索工具中间件调控器，拦截模型与工具的交互以记录有依据的证据，并应对停滞或预算耗尽情况；同时提供可复用的分层技能系统，包括策略技能和访问技能，以增强智能体的搜索过程，避免在多次运行中重复失败的搜索模式。在WideSearch和GISA上，SearchOS在所有评估的单智能体和多智能体基线中领先各项指标，为实现鲁棒的信息获取协作铺平了道路。

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.

SearchOS-V1: 面向鲁棒开放域信息搜寻的智能体协作

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

摘要

Support