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.

翻译：定量系统药理学（QSP）建模在药物研发中至关重要，但其所需的大量时间投入限制了领域专家的处理效率。本文提出 GRASP——一种集成人机对话界面的多智能体图推理框架——该框架将 QSP 模型编码为类型化生物知识图谱，并将其编译为可执行的 MATLAB/SimBiology 代码，同时保持单位一致性、质量平衡及生理约束。通过包含“理解”（对遗留代码进行图重构）与“行动”（基于约束检查的语言驱动修改）的两阶段工作流，由状态机协调迭代验证过程。GRASP 围绕新实体执行广度优先参数对齐，以揭示相关参量并推荐生物学合理的默认值，并通过自动执行与诊断直至收敛。在采用大语言模型作为评判者的对比评估中，GRASP 在生物学合理性、数学正确性、结构保真度及代码质量方面均优于领域专家指导的思维链与思维树基线方法（得分约 9–10/10 对比 5–7/10）。广度优先对齐在依赖关系发现、单位一致性及参数范围校验方面达到 F1 分数 0.95。这些结果表明，基于图结构的智能体工作流能够使 QSP 模型开发兼具易用性与严谨性，使领域专家能够通过自然语言描述机制，同时不牺牲生物医学保真度。