arXiv cs.AI· Qingyuan Zeng, Ziyang Chen, Pengxiang Cai, Zixin Guan, Anglin Liu, Lang Qin, Xinyao Lai, Jintai Chen·· 12 小时前AI 评分31
SCENE：将广泛生物医学知识情境化为场景命题的双层多智能体框架
Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
AI 导读
SCENE 是一个双层多智能体框架，把广泛生物医学知识转化为可检验、场景落地的命题，上层将知识转为搜索方向并对齐数据集 schema，下层用多目标优化筛选兼顾证据强度与数据支持的命题。在临床试验场景中，SCENE 发现具有异质性治疗获益的患者亚组并优于现有基线；在 LINCS L1000 研究中，它识别出目标-响应匹配强、阳性率高的扰动情境。
正文 · 原文
Abstract:Biomedical discovery often requires connecting broad biomedical knowledge with specific experimental or clinical data. Background knowledge suggests relevant mechanisms but is usually too general to map directly onto dataset variables, while data-driven patterns can be dataset-specific and hard to interpret mechanistically. We study this missing link as knowledge contextualization: transforming broad biomedical knowledge into evidence-supported, scenario-grounded propositions that domain experts can inspect, replay, and validate. We propose SCENE, a bi-level multi-agent framework that treats knowledge contextualization as iterative search. The upper level converts broad knowledge into search directions and grounds them in the dataset schema. The lower level executes these directions through multi-objective optimization to identify concrete propositions that balance evidential strength and data support. Feedback between the two levels progressively refines the search. We evaluate SCENE in two settings: discovering patient subgroups with heterogeneous treatment benefits in clinical trial scenarios, and identifying context-specific biological responses in LINCS L1000 studies. In clinical trials, SCENE discovers specific, well-supported subgroups and outperforms existing baselines. In L1000 studies, SCENE identifies perturbational contexts with strong target-response matching and high positive rates. These results show that SCENE bridges broad knowledge and scenario-specific evidence, producing traceable, inspectable hypotheses for follow-up validation.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.27082 [cs.AI] |
| (or arXiv:2605.27082v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.27082 arXiv-issued DOI via DataCite |
Submission history
From: Qingyuan Zeng [view email]
[v1]
Tue, 26 May 2026 14:33:03 UTC (1,139 KB)
[v2]
Thu, 22 Oct 2026 18:54:23 UTC (1,438 KB)
来源：arXiv cs.AI · arxiv.org