# Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning

arXiv: https://arxiv.org/abs/2506.02911 · HTML: https://mlsanity.com/paper/2506.02911/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 18 of its 73 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025)
- [The Impact of Reasoning Step Length on Large Language Models](https://mlsanity.com/paper/2401.04925/) (2024)
- [DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2503.00223/) (2025)
- [Self-Reflection in LLM Agents: Effects on Problem-Solving Performance](https://mlsanity.com/paper/2405.06682/) (2024)
- [Supervising the search process produces reliable and generalizable information-seeking agents](https://mlsanity.com/paper/2502.13957/) (2025)
- [Language-Enhanced Representation Learning for Single-Cell Transcriptomics](https://mlsanity.com/paper/2503.09427/) (2025)
- [A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following](https://mlsanity.com/paper/2501.08187/) (2025)
- [Celler:A Genomic Language Model for Long-Tailed Single-Cell Annotation](https://mlsanity.com/paper/2504.00020/) (2025)

## Built on by (most cited first, 8 of 8)

- [SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models](https://mlsanity.com/paper/2510.06871/) (2025)
- [Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis](https://mlsanity.com/paper/2509.10575/) (2025)
- [Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning](https://mlsanity.com/paper/2511.08024/) (2025)
- [SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation](https://mlsanity.com/paper/2602.23199/) (2026)
- [ES-Merging: Biological MLLM Merging via Embedding Space Signals](https://mlsanity.com/paper/2603.14405/) (2026)
- [MAT-Cell: A Multi-Agent Tree-Structured Reasoning Framework for Batch-Level Single-Cell Annotation](https://mlsanity.com/paper/2604.06269/) (2026)
- [OmicsLM: A Multimodal Large Language Model for Multi-Sample Omics Reasoning](https://mlsanity.com/paper/2605.06728/) (2026)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)

## Abstract (arXiv)

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 workflow, we introduce the CellPuzzles task, where the objective is to assign unique cell types to a batch of cells. This benchmark spans diverse tissues, diseases, and donor conditions, and requires reasoning across the batch-level cellular context to ensure label uniqueness. We find that off-the-shelf large language models (LLMs) struggle on CellPuzzles, with the best baseline (OpenAI's o1) achieving only 19.0% batch-level accuracy. To fill this gap, we propose Cell-o1, a 7B LLM trained via supervised fine-tuning on distilled reasoning traces, followed by reinforcement learning with batch-level rewards. Cell-o1 achieves state-of-the-art performance, outperforming o1 by over 73% and generalizing well across contexts. Further analysis of training dynamics and reasoning behaviors provides insights into batch-level annotation performance and emergent expert-like reasoning. Code and data are available at https://github.com/ncbi-nlp/cell-o1.