Large Language Models (LLMs) excel at many tasks but often falter on complex problems that require structured, multi-step reasoning. We introduce the Diagram of Thought (DoT), a framework that enables a single LLM to build and navigate a mental map of its reasoning. Instead of thinking in a straight line, the model constructs a dynamic diagram of ideas, where it can propose different lines of thought, critique its own steps, and synthesize validated insights into a final conclusion. This process is controller-light: it does not require an external search algorithm or planner, but it does use a deterministic online validator for grammar-constrained typed traces, register constraints, and optional solver checks. To clarify the reliability target of this process, we ground DoT in a mathematical framework from category theory. We interpret accepted typed reasoning records as diagrams in a slice topos and model synthesis of the selected proposer subdiagram as a finite limit. In the predicate fragment, this same object is equivalently a variance-reversed colimit in the opposite information order. The resulting formalism gives an auditable, step-by-step trace of the LLM's typed reasoning and separates semantic guarantees for the typed subtrace from unconstrained natural-language text and uncertified operational edges.
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。
Moving Pictures of Thought: Extracting Visual Knowledge in Charles S. Peirce's Manuscripts with Vision-Language Models
Department of Classics, University Sapienza of Rome(罗马大学萨皮恩扎文学院);Department of Language and Communication Sciences, University of Lausanne(洛桑大学语言与沟通科学系);Campus Fryslân, University of Groningen(格罗宁根大学弗里斯兰校区)
COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion
School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院);Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China(中国电子科学与技术大学深圳高级研究所);School of Computer Science, The University of Sydney(悉尼大学计算机科学学院)
TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence
Sapienza Università di Roma(萨皮恩扎罗马大学);Institute of Informatics and Telematics (IIT)(信息与电信学研究院);National Research Council of Italy (CNR)(意大利国家研究委员会);Department of Excellence in Robotics and AI(机器人与人工智能卓越部门);TeCIP Institute(TeCIP研究所);Scuola Superiore Sant'Anna(圣安娜高级学校)
DiagramNet: An End-to-End Recognition Framework and Dataset for Non-Standard System-Level Diagrams
School of IC, Peking University, Beijing, China(北京大学信息科学技术学院);College of Artificial Intelligence, Xi'an Jiaotong University, Xi'an, China(西安交通大学人工智能学院);Department of Precision Instruments, Tsinghua University, Beijing, China(清华大学精密仪器系);School of Software and Microelectronics, Peking University, Beijing, China(北京大学软件与微电子学院);School of Computer Science, Peking University, Beijing, China(北京大学计算机科学系);Institute of EDA, Peking University, Beijing, China(北京大学EDA研究院);Beijing Advanced Innovation Center for IC, Beijing, China(北京集成电路先进创新中心)