Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-horizon agentic tasks.
arXiv:2607. 07508v1 Announce Type: cross Abstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs).
arXiv:2607. 01083v1 Announce Type: cross Abstract: High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates.
arXiv:2608.29296v1 Announce Type: cross Abstract: Larger batches reduce the variance of stochastic gradients per update and are therefore often expected to accelerate training. Yet whether this stati...
The paper investigates why Group Relative Policy Optimization (GRPO) benefits from per‑prompt normalization by examining the local curvature of the sequence‑level policy gradient. It shows that standard deviation normalization acts as an adaptive gradient, yielding a provably faster convergence rate than unnormalized REINFORCE under mild conditions, with the improvement tied to the average within‑prompt reward standard deviation. The authors also propose IS‑GRPO, an importance‑sampling variant that maintains alignment with the full gradient and offers a tighter convergence guarantee, and empirically validate these theoretical insights on GSM8K and MATH datasets at 1.5B and 7B model scales.
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.
Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixture-of-experts routing. From a trust-region perspective, this mismatch is critical: training-inference divergence governs approximation error in finite-horizon bounds, whereas PPO clipping only gates sampled outward updates, acting as a sampled surrogate rather than a full-policy constraint.
Group Adaptive Clipping Policy Optimization (GAPO) is a plug‑in modification to GRPO methods that adapts the importance‑sampling clipping boundary based on rollout advantage. By allowing rollouts with larger learning signals to receive proportionally greater update headroom, GAPO addresses the limitation of fixed clipping that suppresses rare but informative rollouts. Experiments on Qwen and Llama models show that GAPO consistently improves Pass@1 and Pass@k on math reasoning and coding benchmarks where base model pass rates are low.
arXiv:2606. 08446v1 Announce Type: cross Abstract: Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive.
arXiv:2608. 19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models.
Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the substantial memory overhead of conventional proximal policy optimization (PPO) and achieving strong performance on long-horizon interactive tasks.
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.