让药理学家用自然语言构建精准的药物模型，自动校验生物合理性。
GRASP: Graph Reasoning Agents for Systems Pharmacology with Human-in-the-Loop
- 用知识图谱+多智能体框架，把药理模型转为可执行代码
- 自动发现变量依赖，95%准确率匹配单位和取值范围
- 适合药理专家快速建模，无需编程但保证科学严谨性
定量系统药理学（QSP）建模对新药研发至关重要，但耗时长、门槛高。本文提出GRASP——一种带人机交互的多智能体图推理框架，将QSP模型编码为带类型的生物知识图谱，并编译为保留单位、质量守恒和生理约束的MATLAB/SimBiology代码。采用两阶段工作流： extsc{Understanding}（重构旧代码）与 extsc{Action}（语言驱动修改并验证约束），由状态机协调并迭代验证。GRASP通过广度优先参数对齐，自动识别新实体的依赖项，并提出符合生物学意义的默认值，持续执行与诊断直至收敛。在头对头评估中，使用大模型评分，GRASP在生物合理性、数学正确性、结构保真度和代码质量上均优于人类专家引导的思维链与思维树基线（约9–10/10对比5–7/10）。广度优先对齐在依赖发现、单位与取值范围上达到F1=0.95。结果表明，图结构化的智能体流程可使QSP建模既高效又严谨，让领域专家以自然语言描述机制，同时不牺牲生物医学准确性。
原文摘要 · Abstract (English)
Quantitative Systems Pharmacology (QSP) modeling is essential for drug development but it requires significant time investment that limits the throughput of domain experts. We present \textbf{GRASP} -- a multi-agent, graph-reasoning framework with a human-in-the-loop conversational interface -- that encodes QSP models as typed biological knowledge graphs and compiles them to executable MATLAB/SimBiology code while preserving units, mass balance, and physiological constraints. A two-phase workflow -- \textsc{Understanding} (graph reconstruction of legacy code) and \textsc{Action} (constraint-checked, language-driven modification) -- is orchestrated by a state machine with iterative validation. GRASP performs breadth-first parameter-alignment around new entities to surface dependent quantities and propose biologically plausible defaults, and it runs automatic execution/diagnostics until convergence. In head-to-head evaluations using LLM-as-judge, GRASP outperforms SME-guided CoT and ToT baselines across biological plausibility, mathematical correctness, structural fidelity, and code quality (\(\approx\)9--10/10 vs.\ 5--7/10). BFS alignment achieves F1 = 0.95 for dependency discovery, units, and range. These results demonstrate that graph-structured, agentic workflows can make QSP model development both accessible and rigorous, enabling domain experts to specify mechanisms in natural language without sacrificing biomedical fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。