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: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.
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.
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:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.
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:2607. 26119v1 Announce Type: new Abstract: Large reasoning models trained via reinforcement learning (RL) have been increasingly shown to outperform their supervised fine-tuned (SFT) counterparts on mathematical reasoning tasks; Yet the mechanistic basis for this advantage remains unclear.
arXiv:2607. 00531v1 Announce Type: cross Abstract: Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge.
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:2606. 09932v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training.
arXiv:2607. 03065v1 Announce Type: cross Abstract: Reinforcement learning has become a standard post-training recipe for large language models, but dense full-parameter updates create two deployment-relevant bottlenecks: suppressed reasoning performance, often reflected by premature saturation of test-time scaling, and interference when consolidating multiple capabilities through multi-domain training or model merging.
arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.
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.