TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

2025-03-14

AI Summary

This work addresses the challenge of generating precise, individualized treatment recommendations in precision medicine. We propose TxAgent, an AI-powered therapeutic agent that introduces a novel architecture integrating multi-level pharmacological reasoning—spanning molecular mechanisms, pharmacokinetics, and clinical evidence—with patient-specific constraint modeling and iterative cross-source evidence validation. TxAgent incorporates 211 FDA- and Open Targets–validated tools to enable robust drug name normalization, real-time biomedical knowledge retrieval, and guideline-aligned closed-loop decision-making. Evaluated on five newly constructed benchmarks comprising 3,168 drug-related tasks and 456 personalized clinical scenarios, TxAgent achieves 92.1% accuracy—significantly outperforming GPT-4o and DeepSeek-R1 (671B). The system delivers clinically compliant, low-adverse-event-risk, and fully interpretable treatment recommendations tailored to individual patients.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Develops AI for personalized therapeutic recommendations using multimodal models.
• Analyzes drug interactions and contraindications for patient-specific strategies.
• Integrates real-time biomedical knowledge to enhance clinical decision-making.

Innovation

• Multi-step reasoning for personalized treatment recommendations
• Real-time biomedical knowledge retrieval from 211 tools
• Integration of molecular, pharmacokinetic, and clinical drug interactions