IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Jinesis AI Lab（Jinesis AI实验室）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；EuroSafeAI；Carnegie Mellon University（卡内基梅隆大学）；Amazon（亚马逊）
Ivaxi Sheth, Zhijing Jin, Bryan Wilder, Dominik Janzing, Mario Fritz
In the presence of confounding between an endogenous variable and the outcome, instrumental variables (IVs) are used to isolate the causal effect of the endogenous variable. Identifying valid instruments requires interdisciplinary knowledge, creativity, and contextual understanding, making it a non-trivial task. In this paper, we investigate whether large language models (LLMs) can aid in this task. We perform a two-stage evaluation framework. First, we test whether LLMs can recover well-established instruments from the literature, assessing their ability to replicate standard reasoning. Second, we evaluate whether LLMs can identify and avoid instruments that have been empirically or theoretically discredited. Building on these results, we introduce IV Co-Scientist, a multi-agent system that proposes, critiques, and refines IVs for a given treatment-outcome pair. We also introduce a statistical test to contextualize consistency in the absence of ground truth. Our results show the potential of LLMs to discover valid instrumental variables from a large observational database.
Disentangled Instrumental Variables for Causal Inference with Networked Observational Data
School of Computer Science and Engineering（计算机科学与工程学院）；Guangxi Key Lab of MSMI（广西 MSMI 重点实验室）；MOE Key Lab of EBIT, Guangxi Normal University（教育部 EBIT 重点实验室，广西师范大学）；School of Computer Science and Technology（计算机科学与技术学院）；University of South Australia（南澳大利亚大学）；School of Information Technology and Mathematical Sciences（信息科技与数学科学学院）；China University of Mining and Technology（中国矿业大学）
CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
Tsinghua University（清华大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）；University of Chicago（芝加哥大学）；Adobe
Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA
School of Microelectronics, Tianjin University（天津大学微电子学院）；Department of Orthopedics, Affiliated Kunshan Hospital of Jiangsu University（江苏大学附属昆山医院骨科部）；Department of Clinical Laboratory, The Third Central Hospital of Tianjin（天津第三中心医院临床实验室）；School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?
New York University（纽约大学）；McGill University（麦吉尔大学）；Mila - Quebec Artificial Intelligence Institute（魁北克人工智能研究所）；CIFAR Learning in Machines and Brains Program（CIFAR 机器与大脑学习计划）；The University of Utah（犹他大学）
CausalGame: Benchmarking Causal Thinking of LLM Agents in Games
MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Carnegie Mellon University（卡内基梅隆大学）；Hong Kong Baptist University（香港浸会大学）；University of Oxford（牛津大学）；New York University, Abu Dhabi（纽约大学阿布扎比分校）
Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?
Mila - Quebec AI Institute（魁北克人工智能研究所）；McGill University（麦吉尔大学）；University of California Berkeley（加州大学伯克利分校）；New York University（纽约大学）；Meta FAIR；MIT Media Lab（麻省理工学院媒体实验室）；Montreal Neurological Institute（蒙特利尔神经科学研究所）
