MAT-Cell achieves 75.5% average accuracy on single-cell annotation benchmarks using multi-agent tree reasoning and debate, outperforming CoT (64.2%) and scPilot (51.9%) baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.QM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MAT-Cell: A Multi-Agent Tree-Structured Reasoning Framework for Batch-Level Single-Cell Annotation
MAT-Cell achieves 75.5% average accuracy on single-cell annotation benchmarks using multi-agent tree reasoning and debate, outperforming CoT (64.2%) and scPilot (51.9%) baselines.