MRFoundry：知识引导的智能体循环，用于端到端 MRI 研究
MRFoundry: Knowledge-guided agent loops for end-to-end MRI research
AI 导读
研究者发布开源可扩展的 MRFoundry 包，将 MRI 领域知识接入智能体的操作与输出检查，支持本地项目记忆和经审核的贡献共享。配套的 MRI Agent Bench 显示，在跨 24 种任务类型、十款模型的 240 组 Core 配对评测中，全检查通过完成率从 67.5% 提升至 78.3%；134 组 Hard 配对从 36.6% 提升至 44.8%。该包已在开源环境公开可用。
正文 · 原文
Abstract:AI agents can write code, use scientific software, and revise computational workflows, opening new possibilities for MRI research. Effective assistance requires connecting acquisition physics, data conventions, specialized tools, and scientific validation. We present MRFoundry, an open-source, extensible package that connects MRI knowledge to agent actions and output checks. Project-local memory preserves decisions and evidence, while reviewed contributions allow researchers to improve shared guidance. Researcher-supervised examples demonstrate skill-guided sequence auditing and acquired-data reconstruction, connecting tool use, output checks, and documented decisions. Alongside MRFoundry, we introduce MRI Agent Bench to compare agents with and without the package across models and MRI task domains. Across 240 paired Core evaluations spanning 24 task types and ten models, all-checks-passed completion increased from 67.5% without MRFoundry to 78.3% with it. Across 134 Hard pairs, completion increased from 36.6% to 44.8%. MRFoundry makes MRI workflow expertise available as reusable guidance that researchers can inspect, adapt, and extend within existing agent and scientific software environments. MRFoundry is openly available at this https URL.
| Comments: | 18 pages, including 6 pages of Supporting Information. Code: this https URL |
| Subjects: | Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13289 [eess.IV] |
| (or arXiv:2611.13289v1 [eess.IV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13289 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ke Wang [view email]
[v1]
Mon, 9 Nov 2026 21:54:54 UTC (11,406 KB)
来源：arXiv cs.AI · arxiv.org