Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning

• URL: http://arxiv.org/abs/2605.04066v2
• Date: Thu, 07 May 2026 04:57:40 GMT
• Title: Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
• Abstract summary: Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs)<n>Existing methods typically rely on static policy optimization schemes that misalign with the model's evolving reasoning capabilities.<n>We propose Adaptive Power-Mean Policy Optimization (APMPO), which comprises two main innovations: Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC)
• Score: 25.337475849019842
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically rely on static policy optimization schemes that misalign with the model's evolving reasoning capabilities. To address this issue, we propose Adaptive Power-Mean Policy Optimization (APMPO), which comprises two main innovations: Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC). Specifically, PMPO introduces a generalized power-mean objective. This enables the model to adaptively transition from the signal-amplifying behavior of the arithmetic mean to the consistency-enforcing behavior of the geometric mean. FAC adaptively adjusts clipping bounds based on real-time reward statistics to overcome the limitations of static mechanisms. Capitalizing on these innovations, APMPO improves learning dynamics and reasoning performance. Extensive experiments on nine datasets across three reasoning tasks showcase the superiority of APMPO over state-of-the-art RLVR-based baselines. For instance, APMPO boosts the average Pass@1 score on mathematical reasoning benchmarks by 3.0 points compared to GRPO when using Qwen2.5-3B-Instruct.

Related papers

• Dynamic Important Example Mining for Reinforcement Finetuning [53.98969373888718]
  Reinforcement fine-tuning (RFT) is increasingly used to strengthen the reasoning abilities of large models.<n>Most data-centric RFT methods rely on static or sample selection, implicitly assuming a sample's value is fixed over training.<n>We propose Dynamic Important Example Mining (DIEM), a principled and fully automated framework that makes data utilization adaptive throughout RFT.
  arXiv  Detail & Related papers  (2026-08-29T13:12:25Z)
• Think2Go: Generative Next POI Recommendation with LLM Reasoning [57.37706163990998]
  Next Point-of-Interest (POI) recommendation task focuses on mining user behavioral preference patterns from historical check-ins to provide personalized suggestions for the next destination.<n>Existing methods rely on shallow contextual information and handcrafted feature interactions to predict the next POI.<n>We propose Think2Go, a novel generative next POI recommendation framework, which enhances the model's comprehension of SID representations and explores diverse spatial-temporal patterns via test-time computational scaling.
  arXiv  Detail & Related papers  (2026-07-31T03:52:20Z)
• DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning [4.844785181175473]
  Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization.<n>Standard scalarization practices, such as Reward Combination and Advantage Combination, suffer from significant drawbacks.<n>We propose Dynamic Variance-adaptive Advantage Optimization (DVAO), which dynamically adjusts combination weights based on the empirical reward variance of each objective.
  arXiv  Detail & Related papers  (2026-05-25T08:55:16Z)
• Meta-Learned Adaptive Optimization for Robust Human Mesh Recovery with Uncertainty-Aware Parameter Updates [0.27998963147546146]
  We propose a novel meta-learning framework to train models and incorporate uncertainty-aware adaptive updates during test-time refinement.<n>Our approach achieves state-of-theart performance, reducing MPJPE by 10.3 on 3DPW and 8.0 on Human3.6M compared to strong baselines.
  arXiv  Detail & Related papers  (2026-03-27T14:16:21Z)
• ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning [32.8666744273094]
  We introduce textbfADORA (textbfAdvantage textbfDynamics via textbfOnline textbfRollout textbfAdaptation), a novel framework for policy optimization.
  arXiv  Detail & Related papers  (2026-02-10T17:40:39Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Multi-Objective Reward and Preference Optimization: Theory and Algorithms [3.316593788543852]
  This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models.<n>ACPO, e-COP, warmPref-PS, PSPL, and MOPO advance RL across average-cost, episodic, and preference-driven paradigms.<n> Collectively, the thesis unifies RL across average-cost, episodic, and preference-driven paradigms, delivering theoretical advances and practical tools for safe and aligned decision-making.
  arXiv  Detail & Related papers  (2025-12-11T12:51:21Z)
• Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving [54.46325690390831]
  We propose Model-based Policy Adaptation (MPA), a general framework that enhances the robustness and safety of pretrained E2E driving agents during deployment.<n>MPA first generates diverse counterfactual trajectories using a geometry-consistent simulation engine.<n>MPA trains a diffusion-based policy adapter to refine the base policy's predictions and a multi-step Q value model to evaluate long-term outcomes.
  arXiv  Detail & Related papers  (2025-11-26T17:01:41Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning [17.928214942495412]
  ACPO employs a dynamic curriculum that orchestrates a principled transition from a stable, near on-policy exploration phase to an efficient, off-policy exploitation phase.<n>We conduct extensive experiments on a suite of challenging multimodal reasoning benchmarks, including MathVista, LogicVista, and MMMU-Pro.<n>Results demonstrate that ACPO consistently outperforms strong baselines such as DAPO and PAPO, achieving state-of-the-art performance, accelerated convergence, and superior training stability.
  arXiv  Detail & Related papers  (2025-10-01T09:11:27Z)
• AM-PPO: (Advantage) Alpha-Modulation with Proximal Policy Optimization [0.0]
  We introduce Advantage Modulation PPO (AM-PPO), a novel enhancement of PPO that adaptively modulates advantage estimates using a dynamic, non-linear scaling mechanism.<n>AM-PPO reshapes the advantage signals to stabilize gradient updates and improve the conditioning of the policy gradient landscape.<n>These findings underscore the potential of advantage modulation as a broadly applicable technique for enhancing reinforcement learning optimization.
  arXiv  Detail & Related papers  (2025-05-21T13:38:45Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)

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.