AI搜索不再原地打转：新框架让信息猎手学会记笔记
你让AI去网上查个东西，它经常查着查着就忘了查过什么，开始重复搜同一个词、浪费预算，最后给你的答案还缺东少西。这篇论文把AI搜索从“凭感觉乱翻”变成了“有地图的探案”：它让多个AI助手共享一张“证据图”，谁查到了什么、还缺什么、哪个方向已经试过失败了，全都记在共享黑板上。这样就不会重复踩坑，还能并行查不同线索，效率翻倍。在测试中，它比现有单AI和多AI系统都强。虽然你明天用不上这个系统本身，但它揭示了一个趋势：未来的AI助手会像人类团队一样，有分工、有记忆、有进度表，而不是一个傻傻地反复搜同一个词。
📄 原文摘要(英文)
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.