EPIC introduces a new PPO-style clipping method that operates at the prefix level rather than token level, using the exact reverse-KL coordinate to regulate policy drift during autoregressive generation. By reformulating generation as a finite-horizon Markov decision process, the authors derive a performance-difference identity that identifies the cumulative likelihood ratio of the generated prefix as the exact importance weight for each policy-improvement step. Experiments on off‑policy reinforcement learning with a sparse mixture‑of‑experts language model demonstrate that EPIC consistently outperforms standard and sequence‑level clipping baselines on mathematical‑reasoning benchmarks while remaining competitive with routing‑replay alternatives.
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:2606. 31575v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a powerful tool for propelling Large Language Models (LLMs) beyond imitation-based training towards more robust reasoning capabilities.
arXiv:2606.22570v2 Announce Type: replace Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning ability of large language mo...
arXiv:2606. 09821v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component of post-training large language models (LLMs).
arXiv:2606. 10968v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning.
arXiv:2606. 29758v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) for Large Language Models increasingly relies on critic-free methods as a practical alternative to actor--critic training.
arXiv:2608. 01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models.
arXiv:2607. 10848v1 Announce Type: new Abstract: Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates.
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:2609.24380v1 Announce Type: new Abstract: RLVR has substantially improved the reasoning capabilities of LLMs. However, existing methods typically parameterize temporal progression in the Markov...
Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates. The dominant PPO-style approach uses the sampled-token importance ratio for two criteria: a proximity criterion, which asks whether the policy has moved too far from the behavior policy, and a direction criterion, which asks whether the update pushes it farther away.
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.