sqpeWhat it contributes
Evaluates agents on 380 tasks requiring both database queries and web evidence. Tasks exercise database-to-search, search-to-database, and parallel reasoning, with an emphasis on preserving constraints across tools.
How to read the evidence
Measures agent coordination and final-answer correctness across tools. It does not isolate semantic operator execution or query optimizer performance, and web evidence can change over time.
We checked the primary publication record and abstract. This profile summarizes author-reported work; it does not claim a full-paper audit, implementation audit, or independent reproduction.