The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.
arXiv:2603. 20510v2 Announce Type: replace Abstract: Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel.
arXiv:2601.16823v3 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genuine r...
arXiv:2610.03695v1 Announce Type: new Abstract: Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language mod...
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.
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.