AI for Bio · Model

TxAgent

Therapeutic-reasoning agent calling 211 drug and clinical tools via ToolUniverse

Text, LLMs & agentsAcademic labUnited StatesMaintained only中文

Overview

NameTxAgent · aliases: TxAgent
Full nameNo separate expanded name
Ambiguous names (not auto-linked)None
FamilyNot a family entry. Single-model entry, not a family
OrganizationHarvard Medical School
Organization typeAcademic lab
CountryUnited States
Model classTherapeutic-reasoning agent
DomainText, LLMs & agents (also: Small molecules)
First release · preprint
Basis: arXiv 2503.10970 v1 submitted source
Other milestones
  • Preprint v1: · arXiv v1 source
Latest update · no later event
Basis: Last TxAgent repository commit (v0.1.3)
No later sourced event found (as of 2026-11-16)
Note: The separate ToolUniverse package is still releasing (v1.5.10 on 2026-11-14); not a TxAgent update source
The most recent sourced event, not a claim that nothing changed since.
StatusMaintained only · No TxAgent commits after 2025-04
OpennessCode: Open
Weights: Open
Open source; pip packages txagent and tooluniverse
Benchmarks reported0 counted · none of the 44
Wet-lab validationNone recorded
Unverified fieldsNone
As of2026-11-16

What it does

A therapeutics reasoning agent that picks among 211 drug and clinical tools via ToolUniverse to answer questions on drug interactions, pharmacokinetics and regulatory status through multi-step reasoning.

Benchmarks reported

None of the 44 benchmarks. This model is on the zero-pairing list.

How it evaluates itself: Five self-built benchmarks; Tool-use ablation

Other evaluations (outside the 44)

  • Five self-built benchmarks (Own task set) Self-reported: DrugPC, BrandPC, GenericPC, TreatmentPC, DescriptionPC: 3,168 drug tasks plus 456 treatment scenarios
  • Tool-use ablation (Comparison against baselines only) Self-reported: ToolRAG ablation over 211 tools, compared with general LLM baselines

Developers report: Developers report higher open-ended drug-reasoning accuracy than GPT-4o and DeepSeek-R1 and generalization across drug-name variants

Independent evidence: No independent evidence found. Only CURE-Bench, built by the same lab

Training data

Group in Figure 7: Public data only.

ClassValueDetail
a. Public databasesYesPublic sources behind the 211 tools, e.g. FDA drug information and Open Targets
b. Private or licensed dataNot disclosed
c. Own wet-lab data used for trainingNo
d. Wet lab used only for validationNo

Wet-lab validation

None. The developers report no wet-lab validation.

Background

  • Organization: Academic lab at Harvard Medical School (also tied to the Kempner Institute and Broad Institute), with MIT Lincoln Laboratory collaborators
  • Funding: Acknowledged funding from the Milken Institute, HMS Dean's Innovation Fund and the Kempner Institute
  • Products and partnerships: Companion tool ecosystem ToolUniverse; the same lab built CURE-Bench (NeurIPS 2025)
  • Related models: Biomni, TxGemma

Reading notes

  1. All evaluations are developer-built task sets outside the 44 benchmarks
  2. Still on the zero-pairing list under this round's relation rules

Caveats

  1. Accuracy is developer-reported only; per-task breakdown only in the full text
  2. No wet-lab validation

Sources

  1. arXiv preprint 2503.10970 (preprint)
  2. GitHub repository mims-harvard/TxAgent (repository)
  3. GitHub repository mims-harvard/ToolUniverse (repository)
  4. Official page zitniklab.hms.harvard.edu (company blog)

Corrections

None recorded.

Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.