SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis
Quick Answer
SP-Mind is an autonomous AI agent that streamlines spatial proteomics analysis, converting natural-language queries into analytical workflows.
Quick Take
SP-Mind is an autonomous AI agent that streamlines spatial proteomics analysis, converting natural-language queries into analytical workflows. It outperforms existing biomedical agents on the SP-Bench benchmark, achieving state-of-the-art results across 102 tasks in 18 categories, thus enhancing scalability and reproducibility in research.
Key Points
- SP-Mind integrates the spatial proteomics analysis pipeline from imaging to phenotype discovery.
- It operates without task-specific fine-tuning, enhancing usability for researchers.
- The SP-Bench benchmark evaluates SP-Mind across diverse tissue types and tasks.
- SP-Mind achieves state-of-the-art performance compared to existing open-source biomedical agents.
- This innovation addresses fragmentation in current spatial proteomics workflows.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Spatial proteomics enables single-cell-resolution characterization of protein expression within tissue architecture, playing a critical role in understanding tumor microenvironments and guiding precision medicine. However, current analysis workflows remain fragmented, requiring expert manual orchestration of heterogeneous tools and limiting research scalability and reproducibility. We present SP-Mind, the first autonomous AI agent designed to unify the spatial proteomics analysis pipeline, from raw multiplexed tissue imaging to downstream phenotype discovery. Equipped with expert-curated biological analysis skills and specialized computational tools, SP-Mind converts natural-language queries into end-to-end analytical workflows without task-specific fine-tuning. To rigorously evaluate its capabilities, we introduce SP-Bench, a comprehensive benchmark spanning diverse tissue types, comprising 102 tasks across 18 distinct categories. Through extensive evaluation on SP-Bench and established downstream tasks, SP-Mind achieves state-of-the-art performance compared to existing open-source biomedical agent baselines.
| Comments: | 23 pages, 6 figures. Accepted to ICML 2026. Equal contribution by Yucheng Yuan and Yuanfeng Ji |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.6; J.3 |
| Cite as: | arXiv:2606.24235 [cs.AI] |
| (or arXiv:2606.24235v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.24235 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: YuCheng Yuan [view email]
[v1]
Tue, 23 Jun 2026 07:24:23 UTC (9,244 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.