Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacological, and clinical data, to evaluate potential safety liabilities of therapeutic targets. This process is inherently iterative and expert-driven, posing challenges in scalability and reproducibility. We present TSAssistant, a multi-agent framework designed to support TSA report drafting through a modular, section-based, and human-in-the-loop paradigm. The framework decomposes report generation into a coordinated pipeline of specialised subagents, each targeting a single TSA section. Specialised subagents retrieve structured and unstructured data as well as literature evidence from curated biomedical sources through standardised tool interfaces, producing individually citable, evidence-grounded sections. Agent behaviour is governed by a hierarchical instruction architecture comprising system prompts, domain-specific skill modules, and runtime user instructions. A key feature is an interactive refinement loop in which users may manually edit sections, append new information, upload additional sources, or re-invoke agents to revise specific sections, with the system maintaining conversational memory across iterations. TSAssistant is designed to reduce the mechanical burden of evidence synthesis and report drafting, supporting a hybrid model in which agentic AI augments evidence synthesis while toxicologists retain final decision authority.

翻译：靶点安全性评估（TSA）需要系统整合异质性证据，包括遗传学、转录组学、靶点同源性、药理学和临床数据，以评估治疗靶点的潜在安全性风险。该过程本质上是迭代性的且依赖专家驱动，在可扩展性和可重复性方面存在挑战。我们提出TSAssistant——一种多智能体框架，通过模块化、分章节和人机协同的范式支持TSA报告草拟。该框架将报告生成分解为协调化的专门子智能体流水线，每个子智能体负责单个TSA章节。专门子智能体通过标准化工具接口从精选生物医学数据源检索结构化与非结构化数据及文献证据，生成可独立引用的循证章节。智能体行为受分层指令架构管控，该系统包含系统提示词、领域特定技能模块和运行时用户指令。其核心特征在于交互式优化循环：用户可手动编辑章节、补充新信息、上传额外资源或重新调用智能体修订特定章节，系统则跨迭代维护对话记忆。TSAssistant旨在减轻证据综合与报告草拟的机械性负担，支持智能体增强证据综合、毒理学家保留最终决策权的混合工作模式。