Solving open-ended science questions remains challenging for large language models, particularly due to inherently unreliable supervision and evaluation. The bottleneck lies in the data construction and reward design for scientific post-training. We develop a large-scale, systematic data processing pipeline that transforms heterogeneous open-source science data into Dr. SCI dataset, which comprises of 1M questions across eight STEM subjects, with explicit verifiable/open-ended splits, scalable difficulty annotation, and fine-grained rubrics that operationalize evaluation for open-ended answers. Building on this dataset, we propose the Dr. SCI post-training pipeline, which redesigns the standard SFT -> RL workflow through three components: (i) Exploration-Expanding SFT, which broadens the model's reasoning pattern coverage prior to RL; (ii) Dynamic Difficulty Curriculum, which adapts training data to the model's evolving scientific capability; and (iii) SciRubric-Guided RL, which enables stable reinforcement learning on open-ended scientific questions via rubric-based evaluation with explicit answer correctness. Qwen3-4B-Base trained using Dr. SCI pipeline achieves 63.2 on GPQA-diamond and 32.4 on GPQA-general, consistently improves over strong post-trained baselines such as o1-mini and GPT-4o, demonstrating substantial gains in scientific reasoning, especially in open-ended settings.
LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models
Research Center for Social Computing（社会计算研究中心）；Interactive Robotics, Harbin Institute of Technology, China（交互机器人学，哈尔滨工业大学，中国）；Beijing Academy of Artificial Intelligence, Beijing, China（北京人工智能研究院，北京，中国）
Playing with Words, Improving with Rewards: Training Language Models for Creative Association
University of Massachusetts Lowell（马萨诸塞大学洛市分校）；Dartmouth College（达特茅斯学院）；University of Amsterdam（阿姆斯特丹大学）；Pennsylvania State University（宾夕法尼亚州立大学）；Amazon AGI（亚马逊人工智能研究院）
Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China（计算与智能研究所，哈尔滨工业大学，深圳，中国）；Peng Cheng Laboratory, Shenzhen, China（鹏城实验室，深圳，中国）
Language Imbalance Driven Rewarding for Multilingual Self-improving
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Wuhan AI Research（武汉人工智能研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to Reason
GSAI, Renmin University of China（清华大学）；Large Language Model Department, Tencent（腾讯大语言模型部门）；University of Macau（澳门大学）；School of Computer Science, Wuhan University（武汉大学计算机学院）
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所认知与决策智能复杂系统重点实验室）；China Merchants Bank（中国 Merchants 银行）
Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；School of Information, Renmin University of China（中国人民大学信息学院）；Kuaishou Technology（快手科技）
SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；School of Computer Science（计算机科学学院）；Baidu Inc.（百度公司）；School of Computer Science, Wuhan University（武汉大学计算机学院）
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；National University of Singapore（新加坡国立大学）；Chinese University of Hong Kong（香港中文大学）；University of Oxford（牛津大学）；Tsinghua University（清华大学）
MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
Nanyang Technological University（南洋理工大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；Wuhan University（武汉大学）；National University of Singapore（新加坡国立大学）；University of New South Wales（新南威尔士大学）；MiroMind；The Chinese University of Hong Kong（香港中文大学）
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
University of Chinese Academy of Sciences（中国科学院大学）；Dalian University of Technology（大连理工大学）；UNSW Sydney（新南威尔士大学悉尼分校）；Shenzhen University of Advanced Technology（深圳理工大学）；Xiamen University（厦门大学）
Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt（普遍知识处理实验室（UKP实验室）计算机科学系海德堡人工智能中心（hessian.AI）达姆施塔特技术大学）；Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA)（康拉德·祖斯卓越学习与智能系统学校（ELIZA））
SEPT: Improving Scientific Named Entity Recognition with Span Representation
我们引入了一个新的科学命名实体识别器，称为SEPT，它代表Span Extractor with Pre-trained Transformers。在最近的论文中，跨度提取器已被证明是一个强大的模型相比，序列标记模型。然而，我们发现，随着预训练的语言模型的发展，跨度提取器的性能似乎变得与序列标记模型相似。为了保持跨度表示的优点，我们对模型进行了欠采样，以平衡正负样本，减少搜索空间。此外，我们简化了原始网络结构，将跨度提取器与BERT结合起来。实验表明，即使是简化的体系结构也能达到相同的性能，SEPT在不涉及关系信息的情况下也能实现科学的命名实体识别，达到了一个新的技术水平。
