Web-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents
Web-CogReasoner:迈向用于网络智能体的多模态知识诱导认知推理
机构 * Southwestern University of Finance and Economics(西南财经大学) ; Shanghai Jiao Tong University(上海交通大学) ; Central South University(中南大学) ; Hithink Research(Hithink研究) ; Westlake University(西湖大学) ; Harbin Institute of Technology(哈尔滨工业大学) ; University of Manchester(曼彻斯特大学) ; University of California, Los Angeles(加州大学洛杉矶分校) ; University of Adelaide(阿德莱德大学) ; Fudan University(复旦大学) ; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院) ; Chengdu Everimaging Science and Technology Co., Ltd(成都亿联科技有限公司)
AI总结 研究将网络智能体能力分解为知识内容学习和认知过程两阶段,提出框架分类知识,构建数据集,基于此用新推理框架开发训练智能体,实验显示其优势,还引入评估套件。
Comments Accepted to ICLR 2026. Our code and data is released at https://github.com/Gnonymous/Web-CogReasoner