Model Discovery Agent：LLM辅助贝叶斯实验设计实现数据高效机制模型发现
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
想用最少实验搞清楚因果机制？MDA 把 LLM 和贝叶斯结合，自动设计实验、发现模型，物理化学生物三领域都刷新了纪录。
Model Discovery Agent (MDA) 将大语言模型作为候选结构提议器，与序贯蒙特卡洛、模拟推断和价值信息等贝叶斯方法结合，用于从少量干预实验中学习因果机制模型。
MDA 在 M-open 设定下运行，当真实模型超出假设类时，预测检查会触发提议器扩展假设空间。在物理、化学和生物学三个基准上，MDA 实现了数据高效的模型学习和可靠的干预预测，创下新 SOTA。
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
Predicting the answer to interventional ``what if'' questions --- the outcome of an action never taken --- requires a \emph{mechanistic}, causal model, not a curve fit; and learning such a model requires \emph{experiments}, because passive data leaves its mechanisms unidentified. Experiments are expensive, so the central problem is \emph{data efficiency}. We present the Model Discovery Agent (MDA), which couples a large language model (LLM), used as a \emph{proposer} of candidate structures, with standard Bayesian machinery --- sequential Monte Carlo (SMC) for parameter and structure posteriors, simulation-based inference (SBI) for intractable likelihoods, and value-of-information (VoI) for experiment design --- to discover latent mechanistic world models from few interventions. MDA operates in the M-open setting: when the truth lies outside the current hypothesis class, a predictive check flags the inadequacy and the proposer expands the hypothesis space with a new model whose parameters are then identified by designed experiments. We show that \emph{discovery and design reinforce}: the design step identifies the mechanism the discovery step proposes, and the identified mechanism improves predictions, enabling further discoveries from the remaining unexplained residuals. On three different benchmarks --- covering physics (\DPbench, \citep{wiemann2026discoverphysics}), chemistry (\CHEMbench, \citep{kabra2026autoscilab}) and biology (\HHbench, a new partially observed single-neuron electrophysiology benchmark we create) --- we show that MDA sets a new SOTA in terms of data-efficient model learning and reliable interventional forecasting ability.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include Model Discovery Agent, 贝叶斯实验设计, 因果模型, LLM.
Source attribution: curated from arXiv cs.AI (@Kevin Murphy).