ScholarQuest is a large-scale benchmark for agentic academic paper search, built from 1,000 computer science topics and four research intents. It includes scalable answer construction and a shared retrieval backend, ScholarBase, enabling reproducible evaluation. Results show agentic methods outperform baseline retrieval, with the best agent achieving 0.314 Recall@100 and 0.355 Recall@All, indicating significant room for improvement.