WisPaper: Your AI Scholar Search Engine

We present textscWisPaper, an end-to-end agent system that transforms how researchers discover, organize, and track academic literature. The system addresses two fundamental challenges. (1)~textitSemantic search limitations: existing academic search engines match keywords but cannot verify whether papers truly address complex research questions; and (2)~textitWorkflow fragmentation: researchers must manually stitch together separate tools for discovery, organization, and monitoring. textscWisPaper tackles these through three integrated modules. Scholar Search combines rapid keyword retrieval with textitDeep Search, in which an agentic model, textscWisModel, validates candidate papers against user queries through structured reasoning. Discovered papers flow seamlessly into Library with one click, where systematic organization progressively builds a user profile that sharpens the recommendations of AI Feeds, which continuously surfaces relevant new publications and in turn guides subsequent exploration, closing the loop from discovery to long-term awareness. On TaxoBench, textscWisPaper achieves 22.26% recall, surpassing the O3 baseline (20.92%). Furthermore, textscWisModel attains 93.70% validation accuracy, effectively mitigating retrieval hallucinations.