ncbi
/

Cell-o1

@@ -10,6 +10,8 @@ tags:
 # Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning
 > [!Note]
 > Please refer to our [repository](https://github.com/ncbi-nlp/cell-o1) and [paper](https://www.arxiv.org/abs/2506.02911) for more details.
@@ -17,6 +19,9 @@ tags:
 Cell type annotation is a key task in analyzing the heterogeneity of single-cell RNA sequencing data. Although recent foundation models automate this process, they typically annotate cells independently, without considering batch-level cellular context or providing explanatory reasoning. In contrast, human experts often annotate distinct cell types for different cell clusters based on their domain knowledge.
 To mimic this expert behavior, we introduce ***CellPuzzles***—a benchmark requiring unique cell-type assignments across cell batches. Existing LLMs struggle with this task, with the best baseline (OpenAI's o1) achieving only 19.0% batch accuracy. To address this, we present ***Cell-o1***, a reasoning-enhanced language model trained via SFT on distilled expert traces, followed by RL with batch-level rewards. ***Cell-o1*** outperforms all baselines on both cell-level and batch-level metrics, and exhibits emergent behaviors such as self-reflection and curriculum reasoning, offering insights into its interpretability and generalization.
 ## 🚀 How to Run Inference

 # Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning
 > [!Note]
 > Please refer to our [repository](https://github.com/ncbi-nlp/cell-o1) and [paper](https://www.arxiv.org/abs/2506.02911) for more details.
 Cell type annotation is a key task in analyzing the heterogeneity of single-cell RNA sequencing data. Although recent foundation models automate this process, they typically annotate cells independently, without considering batch-level cellular context or providing explanatory reasoning. In contrast, human experts often annotate distinct cell types for different cell clusters based on their domain knowledge.
 To mimic this expert behavior, we introduce ***CellPuzzles***—a benchmark requiring unique cell-type assignments across cell batches. Existing LLMs struggle with this task, with the best baseline (OpenAI's o1) achieving only 19.0% batch accuracy. To address this, we present ***Cell-o1***, a reasoning-enhanced language model trained via SFT on distilled expert traces, followed by RL with batch-level rewards. ***Cell-o1*** outperforms all baselines on both cell-level and batch-level metrics, and exhibits emergent behaviors such as self-reflection and curriculum reasoning, offering insights into its interpretability and generalization.
+<p align="center">
+  <img src="assets/overview.png" alt="CellPuzzles Overview" width="95%">
+</p>
 ## 🚀 How to Run Inference