VESTA: Visual Exploration with Statistical Tool Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918532608950272 |
|---|---|
| author | Rudman, William Divekar, Abhishek Jain, Kanishk Joseph, Sebastian Offner, Stella S. R. Lease, Matthew Mahowald, Kyle Durrett, Greg Li, Junyi Jessy |
| author_facet | Rudman, William Divekar, Abhishek Jain, Kanishk Joseph, Sebastian Offner, Stella S. R. Lease, Matthew Mahowald, Kyle Durrett, Greg Li, Junyi Jessy |
| contents | Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-language models (VLMs) to iteratively propose and refine statistical models, but these systems struggle on more challenging modeling tasks. To address these limitations, we introduce VESTA: Visual Exploration with Statistical Tool Agents, a framework that equips VLMs with a dynamically growing exploration toolkit to guide model refinement through data transformations, hypothesis-driven visualizations, and robust statistical tests. Unlike prior systems that rely on iterative critique alone, VESTA actively explores data before and during refinement by selecting or creating diagnostic tools, which accumulate in the model's context and can be reused later. We evaluate VESTA against established baselines in three toolkit configurations: no tools, static expert-written tools, and dynamic model-written tools. To support this evaluation, we introduce DAWN (Dataset for Automated Workflows and Numerical Modeling), a benchmark targeting distribution fitting and time series modeling with varying difficulty tiers, and culminating in real-world astronomy tasks including modeling initial mass functions and gravitational-wave chirp signals. We find that VESTA's dynamic tool creation outperforms prior agentic pipelines, with the largest gains on complex and domain-specific tasks. We further show that dynamically generated tools are substantially more sophisticated than those produced by existing visual tool-creation systems, covering more diagnostic categories per function and strongly preferring visual outputs that the VLM critic can reason over directly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00384 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VESTA: Visual Exploration with Statistical Tool Agents Rudman, William Divekar, Abhishek Jain, Kanishk Joseph, Sebastian Offner, Stella S. R. Lease, Matthew Mahowald, Kyle Durrett, Greg Li, Junyi Jessy Artificial Intelligence Computer Vision and Pattern Recognition Computation 68T07, 68T50, 62F15, 62M10, 85A35 I.2.1; I.2.6; I.2.11; G.3; I.2.10; J.2 Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-language models (VLMs) to iteratively propose and refine statistical models, but these systems struggle on more challenging modeling tasks. To address these limitations, we introduce VESTA: Visual Exploration with Statistical Tool Agents, a framework that equips VLMs with a dynamically growing exploration toolkit to guide model refinement through data transformations, hypothesis-driven visualizations, and robust statistical tests. Unlike prior systems that rely on iterative critique alone, VESTA actively explores data before and during refinement by selecting or creating diagnostic tools, which accumulate in the model's context and can be reused later. We evaluate VESTA against established baselines in three toolkit configurations: no tools, static expert-written tools, and dynamic model-written tools. To support this evaluation, we introduce DAWN (Dataset for Automated Workflows and Numerical Modeling), a benchmark targeting distribution fitting and time series modeling with varying difficulty tiers, and culminating in real-world astronomy tasks including modeling initial mass functions and gravitational-wave chirp signals. We find that VESTA's dynamic tool creation outperforms prior agentic pipelines, with the largest gains on complex and domain-specific tasks. We further show that dynamically generated tools are substantially more sophisticated than those produced by existing visual tool-creation systems, covering more diagnostic categories per function and strongly preferring visual outputs that the VLM critic can reason over directly. |
| title | VESTA: Visual Exploration with Statistical Tool Agents |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Computation 68T07, 68T50, 62F15, 62M10, 85A35 I.2.1; I.2.6; I.2.11; G.3; I.2.10; J.2 |
| url | https://arxiv.org/abs/2606.00384 |