The paper introduces Entropy‑Normalized Trust Region (ENTR), a method for asynchronous reinforcement learning that adjusts off‑policy ratio thresholds based on token entropy rather than a single magnitude cut‑off. By recognizing that the natural scale of the ratio is set by entropy, ENTR preserves genuine exploration while filtering out noise from low‑entropy, stale data. Experiments on long‑horizon agentic tasks and mathematical reasoning benchmarks show ENTR outperforms existing asynchronous methods, improving BrowseComp‑Plus performance by 6.9 % and enabling stable training up to 30 policy versions of staleness while matching synchronous GRPO at a 2.6× speedup.
arXiv:2607. 22186v2 Announce Type: replace Abstract: Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse.
arXiv:2602. 04879v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm.
arXiv:2607. 16205v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrasting multiple self generated rollouts.
arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...
arXiv:2605. 25582v2 Announce Type: replace Abstract: Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces distribution mismatch that existing trust-region techniques mitigate primarily by enforcing conservative optimization, often leaving rich training signals underutilized.
arXiv:2606. 03070v1 Announce Type: cross Abstract: Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, but stale responses introduce distribution drift.
arXiv:2509. 02522v3 Announce Type: replace-cross Abstract: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming, however existing RLVR methods often suffer from sparse reward signals and unstable policy gradient updates inherent to RL-based approaches.
arXiv:2603. 25184v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks.
arXiv:2608. 01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models.
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.
BRACE introduces an anchored Bellman‑residual correction to address stale critic bias in asynchronous reinforcement learning for language models. By limiting the correction horizon to a prefix of policy tokens and adding a constant‑weight Monte‑Carlo tail, it separates policy correction from reward propagation. The method improves mean@1 on BrowseComp‑Plus by 2.4% and runs 2.46× faster per step than synchronous training while staying stable 50 updates off‑policy.
arXiv:2606. 10968v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning.