Causal discovery aims to identify causal relationships between variables and is a fundamental problem across the sciences. Traditional statistical causal discovery (SCD) methods rely solely on observational data and ignore the contextual information available in metadata, whereas recent LLM-based methods exploit metadata but treat the large language model (LLM) as a single agent, leaving its judgments vulnerable to memorized or biased associations. To address this gap, we introduce MAC (Multi-Agent Causal Discovery Framework), which casts causal discovery as a multi-agent debate coupled with the autonomous selection of an SCD algorithm. MAC combines two complementary modules, bridged by a Meta Fusion mechanism: a Debate-Coding Module (DCM) that grounds an initial graph in data by autonomously selecting and executing the best-suited SCD algorithm, and a Meta-Debate Module (MDM) that refines the graph through an adversarial Affirmative-Negative-Judge debate over the metadata. Across five benchmark datasets and three metrics (F1, SHD, NHD), MAC achieves the best aggregate performance among five statistical and four LLM-based baselines, ranking first on 10 of 15 evaluation points with Gemini-2.0-Flash -- including a perfect reconstruction of the Earthquake graph -- and remains robust across three backbone LLMs.
Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting
The University of Melbourne（墨尔本大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Peking University（北京大学）；Adelaide University（阿德莱德大学）；Hong Kong Baptist University（香港浸会大学）；The University of Sydney（悉尼大学）；Carnegie Mellon University（卡内基梅隆大学）
Integrating Large Language Model for Improved Causal Discovery
School of Computer Science and Technology, University of Science and Technology of China（计算机科学与技术学院，中国科学技术大学）；University of Science and Technology of China（中国科学技术大学）；Laboratory for Big Data and Decision, University of Science and Technology of China（大数据与决策实验室，中国科学技术大学）；First Affiliated Hospital of University of Science and Technology of China（中国科学技术大学第一附属医院）
Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
University of Houston（德克萨斯大学休斯顿分校）；NEC Laboratories America（NEC美国实验室）；Florida International University（佛罗里达国际大学）；North Carolina State University（北卡罗来纳州立大学）
Learning to Defer for Causal Discovery with Imperfect Experts
University of Oxford（牛津大学）；Mila – Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；ServiceNow Research（ServiceNow研究院）；University of Amsterdam（阿姆斯特丹大学）；Université Laval（拉瓦尔大学）
Can Large Language Models Help Experimental Design for Causal Discovery?
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Hong Kong Baptist University（香港浸会大学）；The University of Sydney（悉尼大学）；Carnegie Mellon University（卡内基梅隆大学）
Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery
University of New South Wales（新南威尔士大学）；School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；School of Computing, Macquarie University（麦考瑞大学计算学院）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织数据61）
Causal Discovery for Explainable AI: A Dual-Encoding Approach
Department of Computer Science, The University of Texas at El Paso（德克萨斯理工大学计算机科学系）；Department of Engineering Education and Leadership, The University of Texas at El Paso（德克萨斯理工大学工程教育与领导力系）
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；University of South Australia（澳大利亚南岸大学）；School of Hong Kong Polytechnic University, Department of Computing（香港理工大学计算机学院）；School of Computer Science and Information Technology, Hefei University of Technology（合肥工业大学计算机科学与信息技术学院）
针对基于约束方法的级联错误及全局评分方法受局部等价类影响的问题，本文提出 HLCD 混合算法，结合 OR 规则候选骨架、评分剪枝与结构评分定向，并在 14 个数据集上验证其优于 7 种现有方法。
Linear Causal Discovery with Interventional Constraints
纳入因果知识和机制对于完善因果模型和改进下游任务（例如设计新治疗方法）至关重要。在本文中，我们引入了一个新的概念，在因果发现，称为介入约束，这从根本上不同于介入数据。虽然干预性数据需要变量的直接扰动，但干预性约束以因果效应的不等式约束的形式对高层次的因果知识进行编码。例如，在Sachs数据集中（Sachs et al.\ 2005年），Akt已被证明是由PIP3激活，这意味着PIP3对Akt发挥积极的因果作用。现有的因果发现方法允许强制执行结构约束（例如，需要从PIP3到Akt的因果路径），但它们仍然可能产生不正确的因果结论，例如学习“PIP3抑制Akt”。干预约束通过明确约束变量对之间的总因果效应来弥合这一差距，确保学习模型尊重已知的因果影响。为了形式化干预约束，我们提出了一个度量来量化线性因果模型的总因果效应，并将问题制定为约束优化任务，使用两阶段约束优化方法求解。我们在真实世界的数据集上评估了我们的方法，并证明了整合干预性约束不仅提高了模型的准确性，确保了与已有发现的一致性，使模型更易于解释，而且还有助于发现新的因果关系，否则识别成本很高。
The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
School of Mathematics, Southeast University, Nanjing 210096, China（数学学院，东南大学，南京210096，中国）；School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China（网络科学与工程学院，东南大学，南京210096，中国）
Causal Discovery from Time-Series Data with Short-Term Invariance-Based Convolutional Neural Networks
Faculty of Computing（计算机学院）；Harbin Institute of Technology（哈尔滨工业大学）；The Artificial Intelligence Institute（人工智能研究所）；The Department of Computer Science（计算机科学系）；The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
