LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling
Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipeline built upon a knowledge graph covering over 7 million Wikipedia entities, which selects relation...
| Authors | Jiarui Zhao, Rongzhi Zhang, Lingchuan Liu et al. |
|---|---|
| Primary category | cs.CL |
| Published | 11 June 2026 |
| Last updated at source | 17 June 2026 |
Connected in the knowledge graph
- meituan-longcat/LoHoSearchDataset · cited by
Models and datasets referencing this paper
- meituan-longcat/LoHoSearchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.