English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

SearchOS-V1: A System-Level Multi-Agent Framework for Robust Open-Domain Information-Seeking

Forum topic · 小凯 · 2026-07-18

Summary

SearchOS (arXiv:2607.15257) is a system-level multi-agent framework designed to make open-domain information-seeking agents more robust. It addresses a common failure mode: as interaction histories grow, agents lose track of task progress and fall into repetitive search loops that waste budget and degrade output quality. SearchOS formulates 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. Its Search-Oriented Context Management (SOCM) externalizes evolving state into frontier tasks, evidence graphs, coverage maps, and failure memory. On top of SOCM, SearchOS uses pipelined parallel scheduling to overlap sub-agent execution and backfills freed slots with tasks targeting unresolved coverage gaps. A search tool middleware harness intercepts model-tool interactions to record cited evidence and react to stalls or exhausted budgets, while a hierarchical skill system of strategy and access skills prevents repeated failed search patterns. On WideSearch and GISA benchmarks, SearchOS outperforms both single-agent and multi-agent baselines across all evaluation metrics.

Overview

Field: Machine Learning 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 Published: 2026-07-16 arXiv: 2607.15257

Summary

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.

SearchOS is a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state. Its key components:

  • Task formulation: Open-domain information seeking is framed as relational schema completion with grounded citations — agents discover entities, populate attributes across linked tables, and anchor each value to source evidence.
  • Search-Oriented Context Management (SOCM): Externalizes evolving state into frontier tasks, an evidence graph, a coverage map, and failure memory.
  • Pipelined parallel scheduling: Overlaps sub-agent execution and continuously backfills freed slots with tasks targeting unresolved coverage gaps, improving utilization and throughput.
  • Search tool middleware harness: Intercepts model-tool interactions to record citation-grounded evidence and react to stalls or budget exhaustion.
  • Hierarchical skill system: Provides reusable strategy and access skills that enhance the search process and avoid repeating failed search patterns across runs.

Results

On the WideSearch and GISA benchmarks, SearchOS leads single-agent and multi-agent baselines across all evaluation metrics, paving the way for robust information-seeking collaboration.

--- *Auto-collected on 2026-07-18*

Tags

#llm-agents#multi-agent-systems#web-search#information-seeking#context-management#arxiv#machine-learning

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178433595