Nowadays, developing reliable DeepResearch-style long-form report generation remains challenging, as training and evaluation lack verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on coarse, pre-defined rubrics that lack sufficient granularity or depend on manually constructed query-specific rubrics that are costly and difficult to scale. In this paper, we propose a pipeline to train preference-grounded query-specific rubric generators tailored for DeepResearch report generation. We first construct a dataset of DeepResearch-style queries annotated with human preferences over paired reports, and train rubric generators via reinforcement learning with a hybrid reward combining preference consistency, format validity, and LLM-based rubric evaluation. We evaluate the resulting rubric generators in two stages. First, on a held-out human-preference test set, the learned rubrics discriminate preferred from rejected reports more effectively than generic, prompted, or SFT-trained rubric alternatives. Second, when used as reward signals to train DeepResearch systems, our rubric generators yield substantial performance gains under both a simple single-agent ReAct framework and a complex multi-agent workflow on the DeepResearch Bench.
Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence
School of Computing, National University of Singapore(新加坡国立大学计算学院);Xiaohongshu Inc.(小红书公司);School of Cyber Science and Technology, Zhejiang University(浙江大学网络空间安全学院);School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);School of Statistics and Data Science, Shanghai University of Finance and Economics(上海财经大学统计与数据科学学院);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)
National University of Singapore(新加坡国立大学);Beijing University of Chemical Technology(北京化工大学);Zhejiang University(浙江大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Southeast University(东南大学);Xiaohongshu(小红书);Peking University(北京大学);MBZUAI(穆罕默德·本·扎耶德人工智能大学)
Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests
Carnegie Mellon University Pittsburgh PA US;INESC-ID, Carnegie Mellon University Pittsburgh PA US;INESC-ID, Instituto Superior T\'ecnico, University of Lisbon Lisbon Portugal;NOVA LINCS\ University Lisbon Caparica Portugal;Carnegie Mellon University;INESC-ID, Carnegie Mellon University;INESC-ID, Instituto Superior T\'ecnico, University of Lisbon;NOVA LINCS\ University Lisbon
CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics
ASUS Intelligent Cloud Services (AICS)(ASUS智能云服务(AICS));Rehabilitation Research Institute of Singapore, Nanyang Technological University(新加坡康复研究院,南洋理工大学);Department of Family Medicine, Taipei Veterans General Hospital(台北荣民总医院家庭医学部);School of Medicine, National Yang Ming Chiao Tung University(国家阳明交通大学医学院);Yong Loo Lin School of Medicine, National University of Singapore(新加坡国立大学 Yong Loo Lin 医学院)
Rubric-Guided Process Reward for Stepwise Model Routing
University of Science and Technology of China(中国科学技术大学);Southeast University(东南大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)