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

TL;DR

<3-5 sentence high-level summary>

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.

Figures (9)

• Figure 1:
• Figure 1: Examples of tool specifications in ToolUniverse. Each specification includes a tool description, which serves as a reference for TxAgent's function calls, and a mapping rule that translates function calls into API requests. The tool description outlines the tool's name, purpose, and the arguments it accepts, including details such as each argument's name, purpose, data type, and whether it is mandatory. a) Tool description for the tool from OpenFDA. b) Tool description for the tool from Open Targets. c) Mapping between Tools in TxAgent and external APIs from from OpenFDA. d) Mapping between Tools in TxAgent and external APIs from from Open Targets.
• Figure 2:
• Figure 2: The multi-agent systems, (i.e., ToolGen, QuestionGen, and TraceGen) that construct the TxAgent-Instruct training dataset for instruction tuning LLM to achieve the capabilities of TxAgent. a) ToolGen: A tool generation multi-agent system that transforms APIs into 211 agent-compatible tools, aggregating them into the ToolUniverse. b) QuestionGen: A question generation multi-agent system designed to extract critical information from documents (e.g., FDA drug documentation) and generate relevant questions. c) TraceGen: A reasoning trace generation multi-agent system, where a Helper agent and a Tool provider module assist the Solver agent in generating step-by-step reasoning and function calls to solve a problem.
• Figure 3: