# PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data

arXiv: https://arxiv.org/abs/2608.16419 · HTML: https://mlsanity.com/paper/2608.16419/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 17 of its 55 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [Self-Distillation Enables Continual Learning](https://mlsanity.com/paper/2601.19897/) (2026)
- [MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval](https://mlsanity.com/paper/2307.00589/) (2023)
- [BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model](https://mlsanity.com/paper/2505.23579/) (2025)
- [Dual-Pathway Circuits of Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2605.13156/) (2026)
- [VCWorld: A Biological World Model for Virtual Cell Simulation](https://mlsanity.com/paper/2512.00306/) (2025)
- [UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating](https://mlsanity.com/paper/2606.21661/) (2026)
- [OwkinZero: Accelerating Biological Discovery with AI](https://mlsanity.com/paper/2508.16315/) (2025)
- [MeMo: Memory as a Model](https://mlsanity.com/paper/2605.15156/) (2026)
- [Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning](https://mlsanity.com/paper/2511.21075/) (2025)
- [AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents](https://mlsanity.com/paper/2605.10876/) (2026)
- [Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning](https://mlsanity.com/paper/2511.08024/) (2025)
- [Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning](https://mlsanity.com/paper/2606.01042/) (2026)

## Abstract (arXiv)

Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that cellular perturbation atlases can instead become reinforcement-learning environments, where measured gene responses provide computable rewards for biological reasoning. We introduce PertMind, which combines trusted-trajectory supervised initialization with gene-, pathway-, and format-level reinforcement signals. Although trained only on forward perturbation-response prediction, PertMind improves response inference in unseen cellular contexts while retaining general language capabilities. It also transfers, without task-specific post-training, to reverse perturbation identification, double-perturbation reasoning, phenotypic-screen prioritization, and biological-process interpretation. PertMind further generates biological profiles that support competitive gene, cell, and donor representations across multiscale downstream tasks. These results support the hypothesis that reinforcement on experimental endpoints can concentrate reusable biological strategies already accessible to pretrained models. More broadly, perturbation-derived reinforcement learning offers a scalable route for transforming expanding experimental atlases into training environments for general-purpose biological reasoning.