Paper 2607.15257
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
- Published
- Jul 2026
- Research lab
- Independent
- Citations
- 0
- GitHub
- 503 stars
01 In brief
Summary
SearchOS is a multi-agent framework for robust open-domain information seeking.
It formulates information-seeking tasks as relational schema completion with grounded citations, where agents discover entities, populate attributes across linked tables, and anchor each value to source evidence.
To manage long-horizon search, it introduces Search-Oriented Context Management (SOCM), which externalizes execution state into a Frontier Task, an Evidence Graph, a Coverage Map, and Failure Memory.
SearchOS uses pipeline-parallel scheduling to overlap sub-agent execution and continuously refill slots with tasks targeting unresolved coverage gaps.
A Search Tool Middleware Harness intercepts model and tool interactions to record grounded evidence and react to stalls or budget exhaustion.
A hierarchical skill system provides reusable strategy and access skills to avoid repeating failed search patterns.
On WideSearch and GISA benchmarks, SearchOS achieves 80.3 item-level F1 on WideSearch and 76.5 set F1 on GISA, outperforming all evaluated single- and multi-agent baselines, with a 13.4-point improvement on GISA set F1.
Ablations show that continuous scheduling reduces time by 24.3% and improves F1, and skills improve item F1 by 2.0 points while reducing search calls by 39.1%.
02 From the paper
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, 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.