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: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.
The paper introduces SORL, a framework that stabilizes off‑policy reinforcement learning for long‑horizon large language model agents. It identifies two key instability sources—token‑level policy granularity mismatches and high‑variance off‑policy updates—and proposes turn‑level importance sampling and clipping‑triggered normalization to align optimization with multi‑turn interactions. Two instantiations, SO‑PPO and SO‑GRPO, are evaluated on open‑domain, multi‑hop, and medical QA benchmarks, as well as on asynchronous RL for mathematical reasoning, showing improved robustness without the need for early stopping or heuristic tuning.
arXiv:2606. 29526v1 Announce Type: new Abstract: Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse.
arXiv:2605.12070v3 Announce Type: replace-cross Abstract: Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy o...
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:2608.20909v1 Announce Type: new Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
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. 18830v1 Announce Type: cross Abstract: Model-Agnostic Meta-Learning (MAML) is a widely used framework for reinforcement learning (RL) that enables efficient transfer by learning global policy parameters that can be rapidly adapted to new tasks.
arXiv:2607. 07508v1 Announce Type: cross Abstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs).
arXiv:2609.36830v1 Announce Type: new Abstract: Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation wi...
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...
Asynchronous reinforcement learning has become the standard way to scale training for language models, but the resulting policy lag biases the critic toward the stale behavior policy. Existing work on...