arXiv Machine Learning October 3, 2026 By Ada Fang, Nikitha Thoduguli, Lukas Fesser, Hanlin Zhang, Sham M. Kakade, Marinka Zitnik

When Do Biological Reasoning Models Use Their Biological Inputs?

Read the original on arXiv Machine Learning →

The study evaluates whether biological reasoning models actually use their biological inputs by testing six models on DNA, protein, and single‑cell tasks. By perturbing one biological input while keeping others fixed, the authors find that many models (e.g., Evo2, ESM3, BioReason, BioReason‑Pro) rely primarily on textual information, with minimal impact from the biological representations. In contrast, models like ChatNT, Prot2Text‑V2, CellWhisperer, and Cell2Sentence‑Scale show greater dependence on their biological inputs, yet overall accuracy gains do not consistently reflect increased biological input contribution.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 16

How Post-Training Shapes Biological Reasoning Models

arXiv:2606. 16517v1 Announce Type: new Abstract: Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins.

By Lukas Fesser, Hanlin Zhang, Michelle M. Li, Eric Wang, Bryan Perozzi, Shekoofeh Azizi, Sham M. Kakade, Marinka Zitnik

llms reinforcement-learning fine-tuning multimodal

Hugging Face Trending Papers

Jun 15

How Post-Training Shapes Biological Reasoning Models

Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are built through post-training, yet how each stage shapes reasoning and generalization remains poorly understood.

llms reinforcement-learning fine-tuning multimodal

arXiv Machine Learning

Sep 22

Tool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks

The paper introduces OmicsBench, a new reasoning benchmark for multi‑omics sequences that includes 1,160 expert‑validated questions across DNA regulation, RNA processing, and protein function tasks, requiring traceable evidence chains. Evaluation of 17 large language models shows that scientific LLMs, while more accurate in classification, often lack valid evidence, suggesting shortcut learning. To address this, the authors propose tool‑augmented on‑policy distillation (TA‑OPD), a post‑training method that improves both evidence grounding and predictive performance across five Qwen3.5 models of varying sizes.

By Jie Ying, Zhefan Wang, Zihong Chen, Zhengqing Li, Jinzhe Li, Gang Li, Jian Liu, Fang Hu, Tao Luo, Zhonghang Yuan, Wanli Ouyang, Stan Z. Li, Fan Yang, Nanqing Dong

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Jun 9

Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction

arXiv:2606. 08147v1 Announce Type: cross Abstract: DNA cis-regulatory elements (CREs) such as enhancers control gene expression levels.

By Yi Duan, Zhao Yang, Jiwei Zhu, Ying Ba, Chuan Cao, Bing Su

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 2

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning

arXiv:2606. 01042v1 Announce Type: cross Abstract: Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression responses for unobserved conditions.

By Xinyu Yuan, Xixian Liu, Jianan Zhao, Yashi Zhang, Hongyu Guo, Jian Tang

llms

arXiv Machine Learning

Jun 2

OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction

arXiv:2510. 17532v2 Announce Type: replace-cross Abstract: Predicting cancer treatment outcomes requires models that are both accurate and interpretable, particularly in the presence of heterogeneous clinical data.

By Raghu Vamshi Hemadri, Geetha Krishna Guruju, Kristi Topollai, Anna Ewa Choromanska

llms nlp reinforcement-learning fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

How Post-Training Shapes Biological Reasoning Models

How Post-Training Shapes Biological Reasoning Models

Tool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks

Biological Reasoning-Informed Regression for Interpretable Regulatory DNA Activity Prediction

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning

OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction