{"paper":{"title":"On Path to Multimodal Historical Reasoning: HistBench and HistAgent","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bingbing Gong, Charles Argon, Daixin Chen, Danni Zhang, Delong Kong, Fulian Xiao, Gen Ye, Guang Ma, Haixia Lian, Han Xia, Haolong Li, Hao Xin, Hongru Wang, Huiting Zeng, Jiacheng Guo, Jiadong Yu, Jiahao Qiu, Jiaqi Li, Jiayi Lu, Jinghan Lu, Jiye Fu, Jundi Cui, Junran Zhou, Kaixuan Huang, Liang Wan, Lin Ding, Ling Yang, Linyan Zhong, Mengdi Wang, Mengqiu Deng, Mengyue Lin, Nan Yi, Peirong Zhou, Ruihuan Ren, Ruipeng Li, Ruixiang Wang, Ruobing Xian, Ruojun Xiong, Ruowei Dai, Shilong Liu, Shuyao Zhou, Shu Zhang, Siran Wang, Tengfei Yu, Tianhui Wang, Tianyi Wang, Tianyuan Ma, Tianze Li, Tongcheng Zhang, Wanyu Luo, Weiao Xing, Weijie Xu, Wentao Zhang, Xiaofeng Zheng, Xiaorui Yang, Xiaoyan Ji, Xiaoyin Zong, Xiaoyu Gao, Xi Gao, Xinrui Sun, Xinzhe Juan, Xuan Qi, Xudong Liu, Xun Jiang, Yang Liao, Yang Wang, Yangyuxuan Yu, Yao Shu, Yao Xiao, Yichao Li, Yifu Lu, Yijia Chen, Yimin Wang, Ying Zhao, Yuchen Mao, Yuchen Yang, Yue Chen, Yujia Wu, Yumeng Jiang, Yuming Cao, Yunfei Chen, Yunjie Zhang, Yunting Gu, Yuxi Wang, Zeyu Wang, Zhanpeng Zhou, Zhaoyi Wu, Zhaoyu Zhang, Zhengyi Chen, Zhenxin Chen, Zhiheng Zhang, Zhi Qiao, Zhuoran Li, Zihao Pu, Zihua Wang, Zijie Guan, Zirui Huang, Zixin Yao, Ziyue Luo","submitted_at":"2025-05-26T17:22:20Z","abstract_excerpt":"Recent advances in large language models (LLMs) have led to remarkable progress across domains, yet their capabilities in the humanities, particularly history, remain underexplored. Historical reasoning poses unique challenges for AI, involving multimodal source interpretation, temporal inference, and cross-linguistic analysis. While general-purpose agents perform well on many existing benchmarks, they lack the domain-specific expertise required to engage with historical materials and questions. To address this gap, we introduce HistBench, a new benchmark of 414 high-quality questions designed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20246","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.20246/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}