arXiv:2608. 02181v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets.
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...
The paper identifies a failure mode in Proximal Policy Optimization (PPO) critics called Value Flattening, where state values vary sharply across intermediate states while critic predictions remain flat. The authors analyze this phenomenon theoretically and empirically, linking it to an implicit variance penalty and redundant updates from temporally correlated states. They propose Sparse Proximal Policy Optimization (SP³O), which applies the value loss to only a few well‑separated states, and demonstrate that this sparse supervision mitigates Value Flattening and improves policy performance on Qwen3‑Base across model sizes and evaluation suites.
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. 25091v1 Announce Type: new Abstract: The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated.
arXiv:2608. 19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models.
arXiv:2606. 20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment.
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.
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.
BCPPO is a new variant of Proximal Policy Optimization that uses Bachelier-inspired cost‑prediction networks to generate a smooth penalty based on disagreement among critics. The method keeps temporal‑difference learning unchanged, applies a saturation‑aware controller to manage cost penalties, and deploys only the policy network. Across extensive experiments, BCPPO outperforms comparators in achieving higher mean returns while maintaining lower or comparable CVaR in all tested tasks.
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.
The paper introduces Best‑Practice Critic Optimization (BPCO), a stable and efficient recipe for training a critic in reinforcement learning for large language models. BPCO combines DPPO, bounded value predictions, Monte Carlo targets, unnormalized policy advantages, and length‑adaptive advantage estimation, allowing the critic to be conditioned on hidden reward information. Experiments on mathematical reasoning tasks with models from 1.5B to 30B parameters show that BPCO consistently outperforms a strong critic‑based baseline and matches or exceeds group‑based methods while sampling only one response per prompt.