arXiv:2608. 16419v1 Announce Type: cross Abstract: Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces.
arXiv:2606. 27752v1 Announce Type: new Abstract: Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions.
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.
arXiv:2607. 18777v1 Announce Type: new Abstract: Evaluating machine learning in scientific domains requires separating correct predictions from correct reasons under realistic distribution shifts.
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.
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.
The paper introduces POISE, a reinforcement learning algorithm that uses a model’s internal states as a value estimator to reduce variance in reinforcement learning with verifiable rewards (RLVR). By employing a lightweight probe that reads internal signals during the forward pass, POISE predicts baselines online and uses a cross‑rollout construction to keep gradients unbiased. Experiments on Qwen3‑4B and OLMo3‑7B‑Instruct‑DPO across six domains show POISE outperforms existing RLVR baselines, offering more stable training and a value model that generalizes across tasks and scales with the policy.
arXiv:2508. 10123v3 Announce Type: replace-cross Abstract: Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT).
arXiv:2510. 13554v2 Announce Type: replace-cross Abstract: The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps.
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.
arXiv:2606. 08816v1 Announce Type: cross Abstract: Predicting the effect of an unseen gene knockout perturbation on transcriptomic gene expression remains a highly challenging problem for virtual cell models.
CellRFT is a reinforcement fine‑tuning framework designed to improve single‑cell perturbation modeling by directly optimizing biological evaluation metrics. It employs policy‑gradient methods to learn from non‑differentiable biological rewards and aggregates multiple rewards hierarchically. Experiments show that CellRFT enhances perturbation prediction across various pretrained models and reveals interactions between different biological criteria, suggesting new ways to shape model behavior and evaluation design.
arXiv:2606. 15866v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models.