Rethinking the Divergence Regularization in LLM RL

• URL: http://arxiv.org/abs/2606.09821v1
• Date: Mon, 08 Jun 2026 17:58:23 GMT
• Title: Rethinking the Divergence Regularization in LLM RL
• Abstract summary: Reinforcement learning (RL) has become a key component of post-training large language models (LLMs)<n>We propose Divergence Regularized Policy Optimization (DRPO), which replaces the hard mask with a smooth advantage-weighted quadratic regularizer on policy shift.<n>DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights.
• Score: 56.952725733148746
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has become a key component of post-training large language models (LLMs). In practice, LLM RL is often off-policy because of training-inference mismatch and policy staleness, making trust-region control essential for stable optimization. Mainstream methods such as PPO and GRPO approximate this control with a ratio-clipping mechanism, but the importance ratio can be a poor proxy for distributional shift in long-tailed vocabularies. Recent work such as DPPO addresses this mismatch by replacing ratio-based clipping with a divergence-based mask, yielding a trust region defined by the sampled token's absolute probability shift. However, DPPO still relies on a hard mask: once a token crosses the trust-region boundary in a harmful direction, its gradient is discarded rather than corrected. To address this, we propose Divergence Regularized Policy Optimization (DRPO), which replaces the hard mask with a smooth advantage-weighted quadratic regularizer on policy shift. DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights that attenuate diverging updates and provide corrective signals beyond the boundary. Experiments across model scales, architectures, and precision settings show that DRPO improves the stability and efficiency of LLM RL training.

Related papers

• Predictive Divergence Masks for LLM RL [44.851813004352046]
  Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates.<n>Recent work DPPO improves the proximity criterion by replacing PPO's ratio-based test with a probability divergence between the behavior and training policies.<n>We propose the predictive divergence mask, which asks whether the next policy-gradient step will increase or decrease the same divergence used by the trust region.
  arXiv  Detail & Related papers  (2026-07-12T17:20:44Z)
• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models [61.74572554094633]
  We argue that ratio clipping is structurally ill-suited for flow models.<n>We propose Flow-DPPO, which replaces ratio clipping with a divergence proximal constraint.<n> Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency.
  arXiv  Detail & Related papers  (2026-06-09T15:59:57Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning [49.25750348525603]
  BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions into dynamic, probability-aware clipping intervals.<n>We show that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.
  arXiv  Detail & Related papers  (2026-03-05T08:03:05Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning [30.908304728142983]
  We propose Query-Adaptive Trust-Region policy optimization (QUATRO)<n>QUATRO directly enforces trust-region constraints through a principled optimization.<n> Empirically verified on diverse mathematical reasoning benchmarks, QUATRO shows stable behavior under increased policy staleness.
  arXiv  Detail & Related papers  (2026-02-04T14:51:04Z)
• A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization [58.116300485427764]
  Reinforcement learning post-training can elicit reasoning behaviors in large language models.<n> token-level correction often leads to unstable training dynamics when the degree of off-policyness is large.<n>We propose a simple yet effective objective, Minimum Prefix Ratio (MinPRO)
  arXiv  Detail & Related papers  (2026-01-30T08:47:19Z)
• Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling [84.00480999255628]
  Reinforcement Learning algorithms for safety alignment of Large Language Models (LLMs) encounter the challenge of distribution shift.<n>Current approaches typically address this issue through online sampling from the target policy.<n>We propose a new framework that leverages the model's intrinsic safety judgment capability to extract reward signals.
  arXiv  Detail & Related papers  (2025-03-13T06:40:34Z)
• Mirror Descent Policy Optimization [41.46894905097985]
  We propose an efficient RL algorithm, called em mirror descent policy optimization (MDPO) MDPO iteratively updates the policy by em approximately solving a trust-region problem. We highlight the connections between on-policy MDPO and two popular trust-region RL algorithms: TRPO and PPO, and show that explicitly enforcing the trust-region constraint is in fact em not a necessity for high performance gains in TRPO.
  arXiv  Detail & Related papers  (2020-05-20T01:30:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.