SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis
Quick Answer
SpaCellAgent is an autonomous LLM-based multi-agent framework that automates spatiotemporal analysis and trajectory inference, achieving over 40% improvement in analytical efficiency across six diverse datasets.
Quick Take
This framework democratizes advanced modeling in computational biology by converting natural language into optimized workflows, reducing the need for manual intervention.
Key Points
- Utilizes a architecture for strategic workflow planning.
- Employs a dynamic tool-orchestration engine for adaptive algorithm selection.
- Features a self-evolution module that refines performance through feedback.
- Demonstrates consistent expert-aligned performance across diverse datasets.
- Code and materials are publicly available for further research.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Spatial and Single-cell transcriptomics are transformative in deciphering cellular dynamics. As the fundamental paradigm for reconstructing cell developmental paths, trajectory inference (TI) is critical. However, existing methods require extensive manual intervention and proficiency in heterogeneous tools, posing a significant barrier to efficient TI analysis. To bridge this gap, we propose SpaCellAgent, an autonomous large language model (LLM) multi-agent framework that automates end-to-end spatiotemporal analysis and narrative generation. SpaCellAgent utilizes a multi-agent architecture for strategic workflow planning, a dynamic tool-orchestration engine for adaptive algorithm selection, and a self-evolution module that iteratively refines performance through feedback. We evaluate SpaCellAgent on six heterogeneous datasets encompassing complex temporal developmental trajectories, diverse sequencing platforms, and spatially-resolved tissue architectures. SpaCellAgent consistently demonstrates over 40\% improvement in analytical efficiency while maintaining expert-aligned performance. By converting natural language specifications into optimized analytical workflows and fully automating the pipeline, SpaCellAgent democratizes advanced spatiotemporal modeling and establishes a scalable, agent-driven paradigm for computational biology. The code and materials are available at this https URL.
| Comments: | 27 pages, 19 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.07467 [cs.AI] |
| (or arXiv:2607.07467v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.07467 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Songhan Wang [view email]
[v1]
Wed, 8 Jul 2026 14:31:46 UTC (18,372 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 →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.