--- title: "TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools" canonical_url: "https://www.modelscope.cn/papers/127064" md_url: "https://www.modelscope.cn/papers/127064.md" arxiv_id: 2503.10970 published: 2025-03-14 last_updated: 2025-03-14 authors: - "Shanghua Gao" - "Richard Zhu" - "Zhenglun Kong" - "Ayush Noori" - "Xiaorui Su" - "Curtis Ginder" - "Theodoros Tsiligkaridis" - "Marinka Zitnik" model_name: TXAGENT model_developer: "哈佛医学院生物医学信息学系" domain: - "自然语言处理" - "医药" - "机器学习" type: - "自然语言处理" - "医药" - "机器学习" - "Artificial Intelligence (cs.AI)" - "Machine Learning (cs.LG)" arxiv_url: "https://arxiv.org/abs/2503.10970" pdf_url: "https://arxiv.org/pdf/2503.10970.pdf" --- # TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools > Precision therapeutics require multimodal adaptive models that generate personalized treatment recommendations. We introduce TxAgent, an AI agent that leverages multi-step reasoning and real-time biomedical knowledge retrieval across a toolbox of 211 tools… 「TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools」是 ModelScope 魔搭社区收录的论文，arXiv 2503.10970，作者为 Shanghua Gao, Richard Zhu, Zhenglun Kong et al.，发表于 2025-03-14，属于 自然语言处理、医药、机器学习 领域。 - **ArXiv**: 2503.10970 - **Published**: 2025-03-14 - **Authors**: Shanghua Gao, Richard Zhu, Zhenglun Kong, Ayush Noori, Xiaorui Su, Curtis Ginder, Theodoros Tsiligkaridis, Marinka Zitnik - **Model**: TXAGENT - **Developer**: 哈佛医学院生物医学信息学系 - **Domain**: 自然语言处理, 医药, 机器学习 - **ArXiv URL**: https://arxiv.org/abs/2503.10970 - **PDF**: https://arxiv.org/pdf/2503.10970.pdf Source: https://www.modelscope.cn/papers/127064 --- > TXAGENT：精准医疗领域的多工具融合与智能推理革命 ## 摘要 本文提出了TXAGENT，一种结合多步骤推理和实时生物医学工具集成的AI代理，用于生成基于证据的个性化治疗建议。研究背景在于精准医疗需要根据个体患者条件最大化疗效并最小化风险，而现有大语言模型（LLMs）虽然能生成流畅的相关响应，但缺乏实时访问更新的生物医学知识的能力，并且容易出现幻觉问题。为此，TXAGENT通过整合211种工具（统称为TOOLUNIVERSE），实现了药物相互作用、禁忌症和患者特异性治疗策略的分析。该模型能够评估药物在分子、药代动力学和临床水平上的相互作用，识别患者的共病和同时用药禁忌症，并根据年龄、遗传因素和疾病进展等个体特征定制治疗策略。此外，TXAGENT通过迭代推理检索和综合来自多个生物医学来源的证据，选择适当的工具以解决需要临床推理和跨源验证的任务。实验结果表明，TXAGENT在五个新基准测试中表现出色，涵盖3,168个药物推理任务和456个个性化治疗场景，准确率达到92.1%，超越了GPT-4o和其他大型LLMs。其贡献在于解决了药物名称变体和描述的泛化问题，显著降低了不同表示下的准确性差异，并展示了在复杂药物推理和个人化治疗推荐中的优越性能。 ## Abstract Precision therapeutics require multimodal adaptive models that generate personalized treatment recommendations. We introduce TxAgent, an AI agent that leverages multi-step reasoning and real-time biomedical knowledge retrieval across a toolbox of 211 tools to analyze drug interactions, contraindications, and patient-specific treatment strategies. TxAgent evaluates how drugs interact at molecular, pharmacokinetic, and clinical levels, identifies contraindications based on patient comorbidities and concurrent medications, and tailors treatment strategies to individual patient characteristics. It retrieves and synthesizes evidence from multiple biomedical sources, assesses interactions between drugs and patient conditions, and refines treatment recommendations through iterative reasoning. It selects tools based on task objectives and executes structured function calls to solve therapeutic tasks that require clinical reasoning and cross-source validation. The ToolUniverse consolidates 211 tools from trusted sources, including all US FDA-approved drugs since 1939 and validated clinical insights from Open Targets. TxAgent outperforms leading LLMs, tool-use models, and reasoning agents across five new benchmarks: DrugPC, BrandPC, GenericPC, TreatmentPC, and DescriptionPC, covering 3,168 drug reasoning tasks and 456 personalized treatment scenarios. It achieves 92.1% accuracy in open-ended drug reasoning tasks, surpassing GPT-4o and outperforming DeepSeek-R1 (671B) in structured multi-step reasoning. TxAgent generalizes across drug name variants and descriptions. By integrating multi-step inference, real-time knowledge grounding, and tool-assisted decision-making, TxAgent ensures that treatment recommendations align with established clinical guidelines and real-world evidence, reducing the risk of adverse events and improving therapeutic decision-making.