# Progressive Multi-Agent Reasoning for Biological Perturbation Prediction

arXiv: https://arxiv.org/abs/2602.07408 · HTML: https://mlsanity.com/paper/2602.07408/

## Key facts

- Cited by 2 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 45 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine](https://mlsanity.com/paper/2308.09442/) (2023)
- [TxGemma: Efficient and Agentic LLMs for Therapeutics](https://mlsanity.com/paper/2504.06196/) (2025)
- [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://mlsanity.com/paper/2408.10609/) (2024)
- [Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning](https://mlsanity.com/paper/2405.07490/) (2024)
- [Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning](https://mlsanity.com/paper/2506.11300/) (2025)
- [Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data](https://mlsanity.com/paper/2501.13126/) (2025)
- [GeneFormer: Learned Gene Compression using Transformer-based Context Modeling](https://mlsanity.com/paper/2212.08379/) (2022)
- [Contextualizing biological perturbation experiments through language](https://mlsanity.com/paper/2502.21290/) (2025)
- [TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction](https://mlsanity.com/paper/2505.14919/) (2025)
- [CellCLIP -- Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning](https://mlsanity.com/paper/2506.06290/) (2025)
- [Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering](https://mlsanity.com/paper/2408.07888/) (2024)
- [From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning](https://mlsanity.com/paper/2510.26336/) (2025)

## Built on by (most cited first, 2 of 2)

- [PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects](https://mlsanity.com/paper/2607.18777/) (2026)
- [Evaluating Agentic Bioinformatics through Function, Evidence, and Validation](https://mlsanity.com/paper/2607.27556/) (2026)

## Abstract (arXiv)

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.