TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools
Shanghua Gao, Richard Zhu, Zhenglun Kong, Ayush Noori, Xiaorui Su, Curtis Ginder, Theodoros Tsiligkaridis, Marinka Zitnik
2025-03-17
Summary
This paper introduces TxAgent, an AI system designed to help doctors make better treatment decisions by analyzing drug interactions and patient information.
What's the problem?
Doctors need to consider many factors when deciding on the best treatment for a patient, including potential drug interactions, the patient's medical history, and other individual characteristics. This can be complex and time-consuming.
What's the solution?
TxAgent uses a variety of tools and knowledge sources to analyze drug interactions, identify potential problems, and tailor treatment strategies to individual patients. It can access information about drugs, patient conditions, and clinical guidelines to make informed recommendations.
Why it matters?
This work matters because it has the potential to improve patient care by helping doctors make more informed and personalized treatment decisions, reducing the risk of adverse events and improving therapeutic outcomes.
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.