arXiv:2606. 26917v1 Announce Type: cross Abstract: Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or misspecified rewards.
arXiv:2602. 21492v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems.
arXiv:2609.36802v1 Announce Type: new Abstract: A key strength of Proximal Policy Optimization (PPO) is its learned critic, which uses historical trajectories collected during reinforcement learning...
arXiv:2609.26355v1 Announce Type: new Abstract: Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted ma...
arXiv:2607. 04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks.
arXiv:2606. 05800v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals.
arXiv:2604. 00860v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a central post-training paradigm for improving the reasoning capabilities of large language models.
arXiv:2606. 05434v1 Announce Type: new Abstract: Group Relative Policy Optimisation (GRPO) has emerged as an effective reinforcement-learning algorithm for aligning language models on reasoning tasks, but it treats every token position and every sampled rollout symmetrically.
arXiv:2606. 16771v1 Announce Type: new Abstract: As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities.
The paper investigates how aligning rounding locations between inference and training can stabilize reinforcement learning for large language models using BF16 precision. By retaining selected intermediates in FP32 until their BF16 outputs in three key regions—RoPE, SwiGLU, and residual RMSNorm—the authors prevent training collapse across four Qwen-family models. The approach keeps the inference engine, matrix‑multiplication and attention kernels, and learning objective unchanged.
The paper introduces COPC, a Coupled Off-Policy Correction method for asynchronous reinforcement learning of large language models. COPC coordinates policy-side and advantage-side corrections by combining token-level ratio masking with two-sided clipped-ratio weighting of TD residuals, addressing both policy mismatch and advantage staleness. Experiments show COPC outperforms existing asynchronous baselines on tool-integrated mathematical reasoning and search tasks, while maintaining training stability and minimal overhead.
arXiv:2608. 09805v1 Announce Type: cross Abstract: Exploration has been a focus of reinforcement learning research for a long time.
The paper addresses instability in off‑policy reinforcement learning for large language models (LLMs) caused by large policy lag. It shows that the correct correction for the prefix‑marginal policy gradient is the cumulative prefix importance ratio, which token‑level weighting fails to capture. To improve stability, the authors propose Minimum Prefix Ratio (MinPRO), a surrogate objective that uses the minimum token‑level ratio in the preceding prefix, and demonstrate its effectiveness on dense and mixture‑of‑experts LLMs across mathematical reasoning benchmarks.