SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Workman, Kenny, Yang, Zhen, Muralidharan, Harihara, Le, Hannah
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917184294354944
author Workman, Kenny
Yang, Zhen
Muralidharan, Harihara
Le, Hannah
author_facet Workman, Kenny
Yang, Zhen
Muralidharan, Harihara
Le, Hannah
contents Spatial transcriptomics assays are rapidly increasing in scale and complexity, making computational analysis a major bottleneck in biological discovery. Although frontier AI agents have improved dramatically at software engineering and general data analysis, it remains unclear whether they can extract biological insight from messy, real-world spatial datasets. We introduce SpatialBench, a benchmark of 146 verifiable problems derived from practical spatial analysis workflows spanning five spatial technologies and seven task categories. Each problem provides a snapshot of experimental data immediately prior to an analysis step and a deterministic grader that evaluates recovery of a key biological result. Benchmark data on frontier models shows that base model accuracy remains low (20-38% across model families), with strong model-task and model-platform interactions. Harness design has a large empirical effect on performance, indicating that tools, prompts, control flow, and execution environment should be evaluated and improved as first-class objects. SpatialBench serves both as a measurement tool and a diagnostic lens for developing agents that can interact with real spatial datasets faithfully, transparently, and reproducibly.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21907
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?
Workman, Kenny
Yang, Zhen
Muralidharan, Harihara
Le, Hannah
Artificial Intelligence
68T07, 92B05
I.2.6; J.3
Spatial transcriptomics assays are rapidly increasing in scale and complexity, making computational analysis a major bottleneck in biological discovery. Although frontier AI agents have improved dramatically at software engineering and general data analysis, it remains unclear whether they can extract biological insight from messy, real-world spatial datasets. We introduce SpatialBench, a benchmark of 146 verifiable problems derived from practical spatial analysis workflows spanning five spatial technologies and seven task categories. Each problem provides a snapshot of experimental data immediately prior to an analysis step and a deterministic grader that evaluates recovery of a key biological result. Benchmark data on frontier models shows that base model accuracy remains low (20-38% across model families), with strong model-task and model-platform interactions. Harness design has a large empirical effect on performance, indicating that tools, prompts, control flow, and execution environment should be evaluated and improved as first-class objects. SpatialBench serves both as a measurement tool and a diagnostic lens for developing agents that can interact with real spatial datasets faithfully, transparently, and reproducibly.
title SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?
topic Artificial Intelligence
68T07, 92B05
I.2.6; J.3
url https://arxiv.org/abs/2512.21907