From Task Executors to Research Partners: Evaluating AI Co-Pilots Through Workflow Integration in Biomedical Research

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weidener, Lukas, Brkić, Marko, Bacci, Chiara, Jovanović, Mihailo, Ulgac, Emre, Dobrin, Alex, Weniger, Johannes, Vlas, Martin, Singh, Ritvik, Meduri, Aakaash
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912749294977024
author Weidener, Lukas
Brkić, Marko
Bacci, Chiara
Jovanović, Mihailo
Ulgac, Emre
Dobrin, Alex
Weniger, Johannes
Vlas, Martin
Singh, Ritvik
Meduri, Aakaash
author_facet Weidener, Lukas
Brkić, Marko
Bacci, Chiara
Jovanović, Mihailo
Ulgac, Emre
Dobrin, Alex
Weniger, Johannes
Vlas, Martin
Singh, Ritvik
Meduri, Aakaash
contents Artificial intelligence systems are increasingly deployed in biomedical research. However, current evaluation frameworks may inadequately assess their effectiveness as research collaborators. This rapid review examines benchmarking practices for AI systems in preclinical biomedical research. Three major databases and two preprint servers were searched from January 1, 2018 to October 31, 2025, identifying 14 benchmarks that assess AI capabilities in literature understanding, experimental design, and hypothesis generation. The results revealed that all current benchmarks assess isolated component capabilities, including data analysis quality, hypothesis validity, and experimental protocol design. However, authentic research collaboration requires integrated workflows spanning multiple sessions, with contextual memory, adaptive dialogue, and constraint propagation. This gap implies that systems excelling on component benchmarks may fail as practical research co-pilots. A process-oriented evaluation framework is proposed that addresses four critical dimensions absent from current benchmarks: dialogue quality, workflow orchestration, session continuity, and researcher experience. These dimensions are essential for evaluating AI systems as research co-pilots rather than as isolated task executors.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Task Executors to Research Partners: Evaluating AI Co-Pilots Through Workflow Integration in Biomedical Research
Weidener, Lukas
Brkić, Marko
Bacci, Chiara
Jovanović, Mihailo
Ulgac, Emre
Dobrin, Alex
Weniger, Johannes
Vlas, Martin
Singh, Ritvik
Meduri, Aakaash
Artificial Intelligence
Artificial intelligence systems are increasingly deployed in biomedical research. However, current evaluation frameworks may inadequately assess their effectiveness as research collaborators. This rapid review examines benchmarking practices for AI systems in preclinical biomedical research. Three major databases and two preprint servers were searched from January 1, 2018 to October 31, 2025, identifying 14 benchmarks that assess AI capabilities in literature understanding, experimental design, and hypothesis generation. The results revealed that all current benchmarks assess isolated component capabilities, including data analysis quality, hypothesis validity, and experimental protocol design. However, authentic research collaboration requires integrated workflows spanning multiple sessions, with contextual memory, adaptive dialogue, and constraint propagation. This gap implies that systems excelling on component benchmarks may fail as practical research co-pilots. A process-oriented evaluation framework is proposed that addresses four critical dimensions absent from current benchmarks: dialogue quality, workflow orchestration, session continuity, and researcher experience. These dimensions are essential for evaluating AI systems as research co-pilots rather than as isolated task executors.
title From Task Executors to Research Partners: Evaluating AI Co-Pilots Through Workflow Integration in Biomedical Research
topic Artificial Intelligence
url https://arxiv.org/abs/2512.04854