Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation
Nanjing University of Information Science \& Technology Nanjing China；East China Normal University Shanghai China；The Hong Kong University of Science；Brown University Providence America；Southwest Jiaotong University Chengdu China；Nanjing University of Information Science \& Technology；East China Normal University；Brown University；Southwest Jiaotong University
提出无需训练的框架Draw with Thought，通过认知思维链推理将科学图表重建为可编辑的mxGraph XML代码，并发布Plot2XML基准，实验证明该方法能生成高保真且结构有效的重建结果。
摘要：
科学图表是跨学科交流结构化知识的重要工具。然而，它们通常以静态光栅图像的形式发布，丢失了符号语义并限制了重用。尽管多模态大语言模型（MLLMs）提供了一条连接视觉与结构的途径，但现有方法缺乏语义控制和结构可解释性，尤其是在复杂图表上。我们提出了Draw with Thought（DwT），这是一个无需训练的框架，通过基于认知的思维链（Chain-of-Thought）推理，引导MLLMs将图表重建为可编辑的mxGraph XML代码。DwT通过将任务分为两个阶段，在无需模型微调的情况下实现了可解释和可控的输出：一是处理感知结构化和语义规范的Coarse-to-Fine Planning（由粗到细规划），二是通过格式引导细化增强的Structure-Aware Code Generation（结构感知代码生成）。为了支持评估，我们发布了Plot2XML，这是一个包含247张真实世界科学图表并带有黄金标准XML注释的基准。在8个MLLMs上的大量实验表明，我们的方法产生了高保真、语义对齐且结构有效的重建，人类评估证实了在准确性和视觉美学上的高度一致，为将静态视觉转换为可执行表示以及推进机器对科学图形的理解提供了可扩展的解决方案。
英文摘要：
Scientific diagrams are vital tools for communicating structured knowledge across disciplines. However, they are often published as static raster images, losing symbolic semantics and limiting reuse. While Multimodal Large Language Models (MLLMs) offer a pathway to bridging vision and structure, existing methods lack semantic control and structural interpretability, especially on complex diagrams. We propose Draw with Thought (DwT), a training-free framework that guides MLLMs to reconstruct diagrams into editable mxGraph XML code through cognitively-grounded Chain-of-Thought reasoning. DwT enables interpretable and controllable outputs without model fine-tuning by dividing the task into two stages: Coarse-to-Fine Planning, which handles perceptual structuring and semantic specification, and Structure-Aware Code Generation, enhanced by format-guided refinement. To support evaluation, we release Plot2XML, a benchmark of 247 real-world scientific diagrams with gold-standard XML annotations. Extensive experiments across eight MLLMs show that our approach yields high-fidelity, semantically aligned, and structurally valid reconstructions, with human evaluations confirming strong alignment in both accuracy and visual aesthetics, offering a scalable solution for converting static visuals into executable representations and advancing machine understanding of scientific graphics.
Learning to Check: Unleashing Potentials for Self-Correction in Large Language Models
School of Software & Microelectronics, Peking University（北京大学软件与微电子学院）；School of Data Science and Engineering, East China Normal University（华东师范大学数据科学与工程学院）
Unleashing the potential of prompt engineering for large language models
Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science（interdisciplinary Research and Application for Data Science省重点实验室）；BNU-HKBU United International College（北京师范大学-香港浸会大学联合国际学院）；Research Center for Mathematics, Beijing Normal University（北京师范大学数学研究中心）
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；ARC Lab, Tencent PCG（腾讯PCG ARC实验室）；The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
Department of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学）；AIIS, ASRI, INMC, ISRC, and IPAI, Seoul National University（人工智能研究所、人工智能研究机构、智能网络中心、智能系统研究所以及人工智能与公共政策研究所，首尔国立大学）
VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
School of Data Science, Fudan University（复旦大学数据科学学院）；ByteDance（字节跳动）；School of Computer Science, Fudan University（复旦大学计算机科学学院）；Research Institute of Intelligent and Complex Systems, Fudan University（复旦大学智能与复杂系统研究院）；Shanghai Innovation Institute（上海创新研究院）
Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；International School, Beijing University of Posts and Telecommunications（北京邮电大学国际学院）；Alibaba Group（阿里巴巴集团）
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
College of AI, Tsinghua University, Beijing, China（清华大学人工智能学院，北京，中国）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室，上海，中国）；The University of Tokyo, Tokyo, Japan（东京大学，东京，日本）
Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study
School of Informatics, Xiamen University, China（厦门大学信息学院）；Baidu Inc., Beijing, China（百度公司）；Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
Department of Computer Science, Princeton University, Princeton, NJ, USA（计算机科学系，普林斯顿大学）；NYU Center for Data Science, New York University, New York, NY, USA（纽约大学数据科学中心）；Department of Psychology, Princeton University, Princeton, NJ, USA（心理学系，普林斯顿大学）
Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
University of Science and Technology of China（中国科学技术大学）；cmss.chinamobile.com（中移（苏州）软件技术有限公司）；Lin Gang Laboratory（林冈实验室）；ShanghaiTech University（上海科技大学）
CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities, Soochow University（苏州大学省级高校数据智能与先进计算重点实验室）；Research Center for SCIR, Harbin Institute of Technology（哈尔滨工业大学SCIR研究中心）；National University of Singapore（新加坡国立大学）
Unlocking the Working Memory of Large Language Models for Latent Reasoning
ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria（林茨ELLIS单元和LIT AI实验室，机器学习研究所，约翰·凯撒大学林茨，奥地利）；NXAI GmbH, Linz, Austria（NXAI公司，林茨，奥地利）
