NeuronSifter：用 Agent-in-Twin 与世界动作模型为中枢神经系统干预排优先级
NeuronSifter: An Agent-in-Twin for Prioritizing Central Nervous System Interventions with World Action Models
NeuronSifter 是一个决策中心的 Agent-in-Twin 框架，让 AI 智能体在持续演化的生物数字孪生中运作，而非依赖固定预测模型。该框架将干预编译为状态条件的目标占据表示，经机制驱动的 World Action Model（WAM）传播，并依据决策不确定性下降幅度选择观测，用于阿尔茨海默病干预场景评估。该论文已被 Haowei Xu 撤回，撤稿理由为投稿未获得全部共同作者授权。
This paper has been withdrawn by Haowei Xu
No PDF available, click to view other formats
Abstract:Effective central nervous system (CNS) intervention requires more than predicting biological responses: a scientific system must determine which intervention, observation, or additional evidence can improve a decision under uncertainty. However, in partially observed neuronal microenvironments, identical predicted outcomes may correspond to different exposure states, biological mechanisms, and intervention risks. We propose NeuronSifter, a decision-centric Agent-in-Twin framework, where an AI agent operates with an evolving biological digital twin rather than a fixed predictive model. NeuronSifter compiles interventions into state-conditional target-occupancy representations, propagates them through a mechanism-grounded World Action Model (WAM), and selects informative measurements based on their expected reduction in decision uncertainty. A shared probabilistic belief state couples intervention simulation, observation selection, and outcome assimilation, enabling the digital twin to continuously refine its decision-relevant representations through externally verified evidence. We evaluate NeuronSifter in Alzheimer's disease intervention scenarios using mechanistic neuronal microenvironment simulations and retrospective clinical endpoint references. The evaluation framework examines adaptive evidence acquisition, uncertainty-aware intervention planning, and robustness under model discrepancy through controlled environments and independent comparisons. NeuronSifter demonstrates how an AI system can actively identify missing evidence, refine biological hypotheses, and optimize intervention decisions under limited experimental budgets. Code is available at this https URL.
| Comments: | The submission was made without obtaining authorization from all co-authors |
| Subjects: | Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2609.35445 [cs.LG] |
| (or arXiv:2609.35445v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.35445 arXiv-issued DOI via DataCite |
Submission history
From: Haowei Xu [view email]
[v1]
Mon, 28 Sep 2026 15:41:54 UTC (808 KB)
[v2]
Tue, 29 Sep 2026 15:30:39 UTC (1 KB) (withdrawn)
[v3]
Sat, 10 Oct 2026 06:29:19 UTC (943 KB)
[v4]
Wed, 14 Oct 2026 14:15:55 UTC (1 KB) (withdrawn)
来源：arXiv：cs.LG · arxiv.org