Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2512.06006 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915657479618560 |
|---|---|
| author | Xuefei Wang Horstmann, Kai A. Lin, Ethan Chen, Jonathan Farhang, Alexander R. Stiles, Sophia Sehgal, Atharva Light, Jonathan Van Valen, David Yue, Yisong Sun, Jennifer J. |
| author_facet | Xuefei Wang Horstmann, Kai A. Lin, Ethan Chen, Jonathan Farhang, Alexander R. Stiles, Sophia Sehgal, Atharva Light, Jonathan Van Valen, David Yue, Yisong Sun, Jennifer J. |
| contents | Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code adaptation costs scientists weeks to months of effort. We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design for this targeted task. We introduce a systematic evaluation framework for agentic code optimization and use it to study three production-level biomedical imaging pipelines. We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions. Our analysis reveals that common, complex agent architectures are not universally beneficial, leading to a practical roadmap for agent design. We open source our framework and validate our approach by deploying agent-generated functions into a production pipeline, demonstrating a clear pathway for real-world impact. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06006 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization Xuefei Wang Horstmann, Kai A. Lin, Ethan Chen, Jonathan Farhang, Alexander R. Stiles, Sophia Sehgal, Atharva Light, Jonathan Van Valen, David Yue, Yisong Sun, Jennifer J. Computer Vision and Pattern Recognition Artificial Intelligence Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code adaptation costs scientists weeks to months of effort. We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design for this targeted task. We introduce a systematic evaluation framework for agentic code optimization and use it to study three production-level biomedical imaging pipelines. We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions. Our analysis reveals that common, complex agent architectures are not universally beneficial, leading to a practical roadmap for agent design. We open source our framework and validate our approach by deploying agent-generated functions into a production pipeline, demonstrating a clear pathway for real-world impact. |
| title | Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.06006 |