Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

• URL: http://arxiv.org/abs/2607.10169v1
• Date: Sat, 11 Jul 2026 07:19:59 GMT
• Title: Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
• Abstract summary: PPO-Clip implicitly measures policy discrepancy using Euclidean metric.<n>This geometric mismatch results in overly conservative updates in low-probability regions while aggressive in high-probability regions, ultimately collapsing exploration.<n>We show that RIPO significantly surpasses existing LLM RL algorithms across seven competition-level benchmarks.
• Score: 44.5236237359076
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This work reveals the fundamental flaw of PPO-Clip: it implicitly measures policy discrepancy using Euclidean metric, which is theoretically inconsistent with the intrinsic geometry on the policy Riemannian manifold. This geometric mismatch results in overly conservative updates in low-probability regions while aggressive in high-probability regions, ultimately collapsing exploration. To correct this geometric flaw, we propose Riemannian Isometric Policy Optimization (RIPO), which guarantees isometric policy updates on the Riemannian manifold, effectively balancing exploration and exploitation. We further show that RIPO achieves a favorable bias-variance trade-off, which stabilizes optimization. Extensive experiments demonstrate that RIPO significantly surpasses existing LLM RL algorithms across seven competition-level benchmarks (up to 60% improvement over GRPO on AIME24).

Related papers

• Rethinking the Divergence Regularization in LLM RL [56.952725733148746]
  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.
  arXiv  Detail & Related papers  (2026-06-08T17:58:23Z)
• Bounded Ratio Reinforcement Learning [62.09379476369526]
  This paper introduces the Bounded Ratio Reinforcement Learning (BRRL) framework to solve on-policy reinforcement learning problems.<n>We develop a policy optimization algorithm called Bounded Policy Optimization (BPO) that minimizes an advantage-weighted divergence between the policy and the analytic optimal solution from BRRL.<n> Notably, our framework also provides a new theoretical lens to interpret the success of the PPO loss, and connects trust region policy optimization and the Cross-Entropy Method (CEM).
  arXiv  Detail & Related papers  (2026-04-20T17:59:01Z)
• Stabilizing Policy Optimization via Logits Convexity [59.242732612484474]
  We show that the convexity of the supervised fine-tuning loss with respect to model logits plays a key role in enabling stable training.<n>Motivated by this observation, we propose Logits Convex Optimization (LCO), a simple yet effective policy optimization framework.
  arXiv  Detail & Related papers  (2026-03-01T07:40:12Z)
• 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)
• Non-Asymptotic Global Convergence of PPO-Clip [23.221917827987625]
  This paper advances the theoretical foundations of the PPO-Clip algorithm by analyzing a deterministic actor-only PPO algorithm within the general RL setting.<n>We derive a non-uniform Lipschitz smoothness condition and a ojasiewicz inequality for the considered problem.
  arXiv  Detail & Related papers  (2025-12-18T14:06:37Z)
• Policy Regularized Distributionally Robust Markov Decision Processes with Linear Function Approximation [10.35045003737115]
  Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ.<n>We propose DR-RPO, a model-free online policy optimization method that learns robust policies with sublinear regret.<n>We show that DR-RPO can achieve suboptimality bounds and sample efficiency in robust RL, matching the performance of value-based approaches.
  arXiv  Detail & Related papers  (2025-10-16T02:56:58Z)
• Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends [64.71326476563213]
  Off-policy reinforcement learning for large language models (LLMs) is attracting growing interest.<n>We present a first-principles derivation for grouprelative REINFORCE without assuming a specific training data distribution.<n>This perspective yields two general principles for adapting REINFORCE to off-policy settings.
  arXiv  Detail & Related papers  (2025-09-29T02:34:54Z)
• StaQ it! Growing neural networks for Policy Mirror Descent [4.672862669694739]
  In Reinforcement Learning (RL), regularization has emerged as a popular tool both in theory and practice.<n>We propose and analyze PMD-like algorithms that only keep the last $M$ Q-functions in memory.<n>We show that for finite and large enough $M$, a convergent algorithm can be derived, introducing no error in the policy update.
  arXiv  Detail & Related papers  (2025-06-16T18:00:01Z)

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.