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

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: 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
• Venue: arXiv: cs.AI
• Published: 2026-07-16
• Collected: 2026-07-17
• URL: http://arxiv.org/abs/2607.15257v1
• PDF: https://arxiv.org/pdf/2607.15257v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers introduce SearchOS, a system-level framework designed to improve the efficiency of multi-agent information-seeking systems. By making search progress explicit and persistent, it helps prevent repetitive loops during failed searches, thereby improving the quality and completeness of the final output.

What the Document Says

• SearchOS is a system-level framework for multi-agent information-seeking.
• It addresses the issue of agents struggling to track task progress as interaction histories grow.
• The system formulates open-domain information seeking as relational schema completion with grounded citations.
• It externalizes the evolving state into Frontier Task, Evidence Graph, Coverage Map, and Failure Memory through Search-Oriented Context Management (SOCM).
• SearchOS uses a pipeline-parallel scheduling mechanism for search agents.
• It introduces a Search Tool Middleware Harness to record grounded evidence, react to stalls or budget exhaustion, and provide a reusable hierarchical skill system.
• On WideSearch and GISA, SearchOS outperforms other single- and multi-agent baselines.

Key Concepts Mentioned

• SearchOS
• Tool-Integrated Large Language Models
• open-domain information seeking
• relational schema completion
• grounded citations
• Search-Oriented Context Management (SOCM)
• Frontier Task
• Evidence Graph
• Coverage Map
• Failure Memory
• pipeline-parallel scheduling
• Search Tool Middleware Harness
• hierarchical skill system
• WideSearch
• GISA

Claims Made by the Document

• SearchOS improves the efficiency of multi-agent information-seeking systems.
• It prevents repetitive loops during failed searches.
• On WideSearch and GISA, SearchOS outperforms other single- and multi-agent baselines.

Evidence Used

• The text states that SearchOS leads all metrics among the evaluated single- and multi-agent baselines on WideSearch and GISA.
• It also mentions that SearchOS helps prevent repetitive loops and improves utilization and throughput.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.