# HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts

arXiv: https://arxiv.org/abs/2603.01396 · HTML: https://mlsanity.com/paper/2603.01396/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities](https://mlsanity.com/paper/2409.11654/) (2024)
- [SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?](https://mlsanity.com/paper/2507.05241/) (2025)
- [CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis](https://mlsanity.com/paper/2407.09811/) (2024)
- [Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder](https://mlsanity.com/paper/2311.02794/) (2023)
- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://mlsanity.com/paper/2408.10609/) (2024)
- [Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows](https://mlsanity.com/paper/2512.16969/) (2025)
- [AutoMind: Adaptive Knowledgeable Agent for Automated Data Science](https://mlsanity.com/paper/2506.10974/) (2025)
- [RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving](https://mlsanity.com/paper/2505.21577/) (2025)
- [AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents](https://mlsanity.com/paper/2510.08511/) (2025)
- [CellForge: Agentic Design of Virtual Cell Models](https://mlsanity.com/paper/2508.02276/) (2025)
- [MatPilot: an LLM-enabled AI Materials Scientist under the Framework of Human-Machine Collaboration](https://mlsanity.com/paper/2411.08063/) (2024)
- [FlowSearch: Advancing deep research with dynamic structured knowledge flow](https://mlsanity.com/paper/2510.08521/) (2025)
- [Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey](https://mlsanity.com/paper/2510.09988/) (2025)

## Built on by (most cited first, 4 of 4)

- [CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction](https://mlsanity.com/paper/2605.07335/) (2026)
- [Evaluating Agentic Bioinformatics through Function, Evidence, and Validation](https://mlsanity.com/paper/2607.27556/) (2026)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)
- [Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models](https://mlsanity.com/paper/2609.27234/) (2026)

## Abstract (arXiv)

Single-cell perturbation studies face dual heterogeneity bottlenecks: (i) semantic heterogeneity--identical biological concepts encoded under incompatible metadata schemas across datasets; and (ii) statistical heterogeneity--distribution shifts from biological variation demanding dataset-specific inductive biases. We propose HarmonyCell, an end-to-end agent framework resolving each challenge through a dedicated mechanism: an LLM-driven Semantic Unifier autonomously maps disparate metadata into a canonical interface without manual intervention; and an adaptive Monte Carlo Tree Search engine operates over a hierarchical action space to synthesize architectures with optimal statistical inductive biases for distribution shifts. Evaluated across diverse perturbation tasks under both semantic and distribution shifts, HarmonyCell achieves a 95% valid execution rate on heterogeneous input datasets (versus 0% for general agents) while matching or even exceeding expert-designed baselines in rigorous out-of-distribution evaluations. This dual-track orchestration enables scalable automatic virtual cell modeling without dataset-specific engineering.