arXiv:2607. 23771v1 Announce Type: new Abstract: Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning.
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 AI.
arXiv:2606. 00229v1 Announce Type: cross Abstract: Natural language is a powerful reasoning medium for language and vision-language models, but it is mismatched to the granularity of continuous control.
arXiv:2608.29988v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are common...
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:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv:2606. 03965v1 Announce Type: cross Abstract: Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control.