NeuronDiscover：基于世界行动模型的神经元微环境机制发现的孪生智能体
NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models
浏览论文内容
中文总结 AI 辅助
NeuronDiscover提出孪生智能体框架，通过世界行动模型耦合预测与实验设计，区分机制变化与模型误差，在模拟和真实数据上提升机制发现效率与验证准确性。
中文摘要 AI 辅助
神经元微环境中的机制发现需要干预和测量，以区分关于溶质转运和神经元反应的相互竞争的解释。预测准确性无法解决这一问题：真实的机制变化和计算孪生中的错误在稀疏观测中留下相同的特征。我们将这种孪生混淆形式化，并在联合机制-差异信念上进行推理，设计能够区分两者的实验。NeuronDiscover是一个孪生智能体框架，其共享的、基于机制的“世界行动模型”（WAM）将预测、干预提议和观测设计耦合在一起；独立裁决的结果更新一个范围限定的“机制-干预-观测-结果”（MIOY）图，其支持的关系编译成带有差异调整接受界限的可执行程序。我们在由独立冻结的更细网格参考求解器裁决的模拟脑液示踪剂转运世界，以及供体不相交的公开皮层神经元电流钳记录上进行了评估。仅计算达到认证终止状态的关系，并将弃权（不执行）计为未解决，在32个源单元上匹配16次实验的预算下，NeuronDiscover在每个分配世界中解决4.0个关系，而最强基线为3.4个，无图修订时为3.2个，假支持率为5%，范围准确率为82%。联合机制-差异获取解决了3.8个关系，而插入式期望信息增益为2.9个；差异调整验证将已接受程序失败率从15%降至9%，接受覆盖率为60%；迁移到记录数据后，每个分配世界产生1.94个关系，对比1.53个。正确性在声明的模型世界和档案记录内进行裁决。
英文摘要
Mechanistic discovery in neuronal microenvironments requires interventions and measurements that separate competing explanations of solute transport and neuronal response. Predictive accuracy cannot settle the question: a real mechanistic change and an error in the computational twin leave the same signature in sparse observations. We formalize this twin confounding and reason over a joint mechanism--discrepancy belief, designing experiments that separate the two. NeuronDiscover is an Agent-in-Twin framework whose shared, mechanism-grounded World Action Model (WAM) couples prediction, intervention proposals, and observation design; independently adjudicated outcomes revise a scoped Mechanism--Intervention--Observation--Outcome (MIOY) graph, whose supported relations compile into executable programs carrying discrepancy-adjusted acceptance bounds. We evaluate on simulated brain-fluid tracer-transport worlds adjudicated by an independently frozen finer-mesh reference solver, and on donor-disjoint public current-clamp recordings of cortical neurons. Counting only relations that reach a certified terminal status, and scoring abstentions as unresolved for every method, at a matched budget of 16 experiments over 32 source units NeuronDiscover resolves 4.0 relations per assigned world against 3.4 for the strongest baseline and 3.2 without graph revision, at 5% false support and 82% scope accuracy. Joint mechanism--discrepancy acquisition resolves 3.8 relations versus 2.9 for plug-in expected information gain; discrepancy-adjusted verification lowers accepted-program failure from 15% to 9% at 60% acceptance coverage; and transfer to the recordings yields 1.94 versus 1.53 relations per assigned world. Correctness is adjudicated within declared model worlds and archival recordings.
发表机构
- Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医学技术研究院）
- Beijing Key Laboratory of Intelligent Neuromodulation and Brain Disorder Treatment（北京智能神经调控与脑疾病治疗重点实验室）
- Department of Radiology, Peking University Third Hospital（北京大学第三医院放射科）
- National Biomedical Imaging Center, College of Future Technology, Peking University（北京大学未来技术学院国家生物医学成像中心）
机构由 AI 辅助整理，请以论文原文为准。
