SGR-Bench
Explore score history ↗SGR-Bench evaluates search agents on state-gated retrieval tasks. It includes 100 expert-curated tasks across 12 public data ecosystems, requiring agents to configure site-specific filters, views, hierarchies, or scopes to retrieve structured answers. Tasks come in goal-oriented and constraint-guided formulations.
- Released
- 2026-05-21
- Institutions
- Beijing University of Technology · Peking University
- Evaluates
- General AI, Information retrieval, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SGR-Bench paper and dataset
No reported scores are on record for this benchmark yet.