Predicting gene regulation responses to biological perturbations requires reasoning about underlying biological causalities. While large language models (LLMs) show promise for such tasks, they are often overwhelmed by the entangled nature of high-dimensional perturbation results. Moreover, recent works have primarily focused on genetic perturbations in single-cell experiments, leaving bulk-cell chemical perturbations, which is central to drug discovery, largely unexplored. Motivated by this, we present LINCSQA, a novel benchmark for predicting target gene regulation under complex chemical perturbations in bulk-cell environments. We further propose PBio-Agent, a multi-agent framework that integrates difficulty-aware task sequencing with iterative knowledge refinement. Our key insight is that genes affected by the same perturbation share causal structure, allowing confidently predicted genes to contextualize more challenging cases. The framework employs specialized agents enriched with biological knowledge graphs, while a synthesis agent integrates outputs and specialized judges ensure logical coherence. PBio-Agent outperforms existing baselines on both LINCSQA and PerturbQA, enabling even smaller models to predict and explain complex biological processes without additional training.
@article{arxiv.2602.07408,
title = {Progressive Multi-Agent Reasoning for Biological Perturbation Prediction},
author = {Hyomin Kim and Sang-Yeon Hwang and Jaechang Lim and Yinhua Piao and Yunhak Oh and Woo Youn Kim and Chanyoung Park and Sungsoo Ahn and Junhyeok Jeon},
journal= {arXiv preprint arXiv:2602.07408},
year = {2026}
}