Episode
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
- Podcast
- Daily Paper Cast
- Published
- Jul 18, 2026
- Duration seconds
- 957
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/b85efd85
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/searchos-v1-towards-robust-open-domain-information-seeking-agent-collaboration/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/searchos-v1-towards-robust-open-domain-information-seeking-agent-collaboration.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 49 | cs.AI, cs.IR Authors: 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 Title: SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration Arxiv: http://arxiv.org/abs/2607.15257v1 Abstract: 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…