Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.29163 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910268873768960 |
|---|---|
| author | Long, Ziyang Li, Xinqi Chen, Junzhou Gao, Yifan Li, Debiao Yang, Hsin-Jung |
| author_facet | Long, Ziyang Li, Xinqi Chen, Junzhou Gao, Yifan Li, Debiao Yang, Hsin-Jung |
| contents | Many recent medical VLM and agent studies are benchmarked on 2D images or comparatively short tool-calling exchanges, whereas real MRI analysis typically demands long, interdependent pipelines that operate on 3D/4D volumetric data. Under these conditions, reactive tool-calling agents are prone to cascading breakdowns triggered by faulty intermediate references, mismatched tool arguments, and limited control over cross-step dependencies. To address this, we introduce BCER (Brain-Cerebellum-Extremity-Reflector), a controller architecture aimed at dependable long-horizon MRI workflow execution. BCER decouples high-level planning from execution and provides bounded local recovery. We assess BCER on a multi-organ MRI benchmark covering brain, prostate, and cardiac tasks with both short- and long-chain workflows, using matched task contracts across controller variants and several backbone models. Relative to reactive baselines, BCER yields consistent improvements in end-to-end execution, with the most pronounced gains observed on long-chain workflows. BCER additionally enables auditability by maintaining explicit links between final outputs and intermediate artifacts and measurements. Code and benchmark are released at https://github.com/Albertlongzi/BCER. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29163 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BCER Agent: Reliable Long-Horizon MRI Workflow Execution via Compilation, Artifact Binding, and Bounded Local Recovery Long, Ziyang Li, Xinqi Chen, Junzhou Gao, Yifan Li, Debiao Yang, Hsin-Jung Image and Video Processing Many recent medical VLM and agent studies are benchmarked on 2D images or comparatively short tool-calling exchanges, whereas real MRI analysis typically demands long, interdependent pipelines that operate on 3D/4D volumetric data. Under these conditions, reactive tool-calling agents are prone to cascading breakdowns triggered by faulty intermediate references, mismatched tool arguments, and limited control over cross-step dependencies. To address this, we introduce BCER (Brain-Cerebellum-Extremity-Reflector), a controller architecture aimed at dependable long-horizon MRI workflow execution. BCER decouples high-level planning from execution and provides bounded local recovery. We assess BCER on a multi-organ MRI benchmark covering brain, prostate, and cardiac tasks with both short- and long-chain workflows, using matched task contracts across controller variants and several backbone models. Relative to reactive baselines, BCER yields consistent improvements in end-to-end execution, with the most pronounced gains observed on long-chain workflows. BCER additionally enables auditability by maintaining explicit links between final outputs and intermediate artifacts and measurements. Code and benchmark are released at https://github.com/Albertlongzi/BCER. |
| title | BCER Agent: Reliable Long-Horizon MRI Workflow Execution via Compilation, Artifact Binding, and Bounded Local Recovery |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2605.29163 |