# TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology

arXiv: https://arxiv.org/abs/2606.19245 · HTML: https://mlsanity.com/paper/2606.19245/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 44 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 5 of 5)

- [LAB-Bench: Measuring Capabilities of Language Models for Biology Research](https://mlsanity.com/paper/2407.10362/) (2024)
- [BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology](https://mlsanity.com/paper/2503.00096/) (2025)
- [Artificial Intelligence for Drug Discovery: Are We There Yet?](https://mlsanity.com/paper/2307.06521/) (2023)
- [SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?](https://mlsanity.com/paper/2512.21907/) (2025)
- [Verifiable Benchmarking of Long-Horizon Spatial Biology](https://mlsanity.com/paper/2605.28065/) (2026)

## Built on by (most cited first, 1 of 1)

- [BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance](https://mlsanity.com/paper/2607.19262/) (2026)

## Abstract (arXiv)

Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions. We introduce TherapeuticsBench Preclinical Pharmacology (TxBench-PP), a verifiable benchmark for small-molecule preclinical pharmacology and the first focused slice of a broader TherapeuticsBench effort across drug-discovery stages and therapeutic modalities. TxBench-PP tests whether agents can recover accurate conclusions from real-world assay data rather than memorized facts from literature. The benchmark contains 100 evaluations indexed by program stage, assay type, and task structure, spanning mechanism-of-action (MoA) and pharmacodynamic (PD) reasoning, compound-target engagement, causal target validation, developability and safety, and translational efficacy. Agents receive realistic workflow snapshots, inspect files in a coding environment, and return structured answers graded deterministically. Across 16 model-harness configurations, comprising 11 models and 4,800 trajectories, no system reliably recovered preclinical pharmacology decisions. The strongest configuration, Claude Opus 4.8 / Pi, passed 59.3% of endpoint attempts (178/300; 95% CI, 51.1-67.6), followed by GPT-5.5 / Pi at 55.3% (166/300; 47.0-63.6).