WisPaper: Your AI Scholar Search Engine

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ju, Li, Zhao, Jun, Chai, Mingxu, Shen, Ziyu, Wang, Xiangyang, Geng, Yage, Ma, Chunchun, Peng, Hao, Li, Guangbin, Li, Tao, Liao, Chengyong, Wang, Fu, Wang, Xiaolong, Chen, Junshen, Gong, Rui, Liang, Shijia, Li, Feiyan, Zhang, Ming, Tan, Kexin, Ye, Junjie, Xi, Zhiheng, Dou, Shihan, Gui, Tao, Ying, Yuankai, Shi, Yang, Zhang, Yue, Zhang, Qi
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Information Retrieval Artificial Intelligence H.3.3; I.2.7
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866908958964318208
author	Ju, Li Zhao, Jun Chai, Mingxu Shen, Ziyu Wang, Xiangyang Geng, Yage Ma, Chunchun Peng, Hao Li, Guangbin Li, Tao Liao, Chengyong Wang, Fu Wang, Xiaolong Chen, Junshen Gong, Rui Liang, Shijia Li, Feiyan Zhang, Ming Tan, Kexin Ye, Junjie Xi, Zhiheng Dou, Shihan Gui, Tao Ying, Yuankai Shi, Yang Zhang, Yue Zhang, Qi
author_facet	Ju, Li Zhao, Jun Chai, Mingxu Shen, Ziyu Wang, Xiangyang Geng, Yage Ma, Chunchun Peng, Hao Li, Guangbin Li, Tao Liao, Chengyong Wang, Fu Wang, Xiaolong Chen, Junshen Gong, Rui Liang, Shijia Li, Feiyan Zhang, Ming Tan, Kexin Ye, Junjie Xi, Zhiheng Dou, Shihan Gui, Tao Ying, Yuankai Shi, Yang Zhang, Yue Zhang, Qi
contents	We present \textsc{WisPaper}, an end-to-end agent system that transforms how researchers discover, organize, and track academic literature. The system addresses two fundamental challenges. (1)~\textit{Semantic search limitations}: existing academic search engines match keywords but cannot verify whether papers truly address complex research questions; and (2)~\textit{Workflow fragmentation}: researchers must manually stitch together separate tools for discovery, organization, and monitoring. \textsc{WisPaper} tackles these through three integrated modules. \textbf{Scholar Search} combines rapid keyword retrieval with \textit{Deep Search}, in which an agentic model, \textsc{WisModel}, validates candidate papers against user queries through structured reasoning. Discovered papers flow seamlessly into \textbf{Library} with one click, where systematic organization progressively builds a user profile that sharpens the recommendations of \textbf{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, \textsc{WisPaper} achieves 22.26\% recall, surpassing the O3 baseline (20.92\%). Furthermore, \textsc{WisModel} attains 93.70\% validation accuracy, effectively mitigating retrieval hallucinations.
format	Preprint
id	arxiv_https___arxiv_org_abs_2512_06879
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	WisPaper: Your AI Scholar Search Engine Ju, Li Zhao, Jun Chai, Mingxu Shen, Ziyu Wang, Xiangyang Geng, Yage Ma, Chunchun Peng, Hao Li, Guangbin Li, Tao Liao, Chengyong Wang, Fu Wang, Xiaolong Chen, Junshen Gong, Rui Liang, Shijia Li, Feiyan Zhang, Ming Tan, Kexin Ye, Junjie Xi, Zhiheng Dou, Shihan Gui, Tao Ying, Yuankai Shi, Yang Zhang, Yue Zhang, Qi Information Retrieval Artificial Intelligence H.3.3; I.2.7 We present \textsc{WisPaper}, an end-to-end agent system that transforms how researchers discover, organize, and track academic literature. The system addresses two fundamental challenges. (1)~\textit{Semantic search limitations}: existing academic search engines match keywords but cannot verify whether papers truly address complex research questions; and (2)~\textit{Workflow fragmentation}: researchers must manually stitch together separate tools for discovery, organization, and monitoring. \textsc{WisPaper} tackles these through three integrated modules. \textbf{Scholar Search} combines rapid keyword retrieval with \textit{Deep Search}, in which an agentic model, \textsc{WisModel}, validates candidate papers against user queries through structured reasoning. Discovered papers flow seamlessly into \textbf{Library} with one click, where systematic organization progressively builds a user profile that sharpens the recommendations of \textbf{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, \textsc{WisPaper} achieves 22.26\% recall, surpassing the O3 baseline (20.92\%). Furthermore, \textsc{WisModel} attains 93.70\% validation accuracy, effectively mitigating retrieval hallucinations.
title	WisPaper: Your AI Scholar Search Engine
topic	Information Retrieval Artificial Intelligence H.3.3; I.2.7
url	https://arxiv.org/abs/2512.06879