Progressive Content Refinement with Decaying Reward Joint LinUCB

• URL: http://arxiv.org/abs/2608.06750v1
• Date: Fri, 07 Aug 2026 03:17:22 GMT
• Title: Progressive Content Refinement with Decaying Reward Joint LinUCB
• Abstract summary: We propose a novel contextual bandit algorithm that explicitly incorporates reward decay modeling.<n>We show that our method achieves significant performance gains over strong baselines.<n>Our ablation study confirms that the integration of reward decay modeling within the bandit framework is crucial for mitigating over-exploitation.
• Score: 2.1290878226779877
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Iterative refinement has significantly enhanced Large Language Model (LLM) performance; however, existing methods ranging from feedback-based Self-Refine to traditional bandit approaches often rely on static options or overlook the saturation effect. This neglect leads to over-exploitation, where the continuous use of identical prompts or arms results in diminishing rewards over time. To address this challenge, we propose a novel contextual bandit algorithm that explicitly incorporates reward decay modeling. Utilizing an Expectation-Maximization (EM) algorithm, our method simultaneously estimates both arm-specific and decay parameters. Furthermore, by embedding prompts as arms, we facilitate the joint learning of arm values, distinguishing our approach from the traditional disjoint Linear Upper Confidence Bound (LinUCB) framework. Experimental results on Sentiment Reversal and GSM8K benchmarks demonstrate that our method achieves significant performance gains over strong baselines. Finally, our ablation study confirms that the integration of reward decay modeling within the bandit framework is crucial for mitigating over-exploitation and optimizing the iterative refinement process.

Related papers

• Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction [52.32112533846212]
  MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions.<n>We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction.<n>We show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling.
  arXiv  Detail & Related papers  (2026-05-19T04:40:50Z)
• Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models [54.597200388738656]
  Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples.<n>We show that many can be written under a common framework, which we call reward score matching (RSM)
  arXiv  Detail & Related papers  (2026-04-19T12:47:52Z)
• Alternating Reinforcement Learning with Contextual Rubric Rewards [2.1172256884504588]
  Reinforcement Learning with Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback.<n>Existing approaches in RLRR are limited to linearly compressing vector rewards into a scalar reward with a fixed weightings.<n>This work proposes Alternating Reinforcement Learning with Rewards (ARL-RR) to overcome the limitations of reward aggregation.
  arXiv  Detail & Related papers  (2026-03-04T04:18:39Z)
• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling [49.41422138354821]
  We propose a principled reward modeling framework that integrates non-negative factor analysis into the Bradley-Terry preference model.<n>BNRM represents rewards through a sparse, non-negative latent factor generative process.<n>We show that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T08:14:11Z)
• Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training [29.56905427210088]
  gradient-ARM is a framework that jointly optimize a rubric generator and a judge using reinforcement learning from preference feedback.<n>We show that gradient-ARM achieves state-of-the-art performance among baselines on benchmarks and significantly improves downstream policy alignment in both offline and online reinforcement learning settings.
  arXiv  Detail & Related papers  (2026-02-02T00:50:53Z)
• SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models [53.19726629537694]
  Post-training alignment of video generation models with human preferences is a critical goal.<n>Current data collection paradigms, reliant on in-prompt pairwise annotations, suffer from labeling noise.<n>We propose SoliReward, a systematic framework for video RM training.
  arXiv  Detail & Related papers  (2025-12-17T14:28:23Z)
• WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training [64.0932926819307]
  We present Warmup-Stable and Merge (WSM), a framework that establishes a formal connection between learning rate decay and model merging.<n>WSM provides a unified theoretical foundation for emulating various decay strategies.<n>Our framework consistently outperforms the widely-adopted Warmup-Stable-Decay (WSD) approach across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-07-23T16:02:06Z)
• Intra-Trajectory Consistency for Reward Modeling [67.84522106537274]
  We develop an intra-trajectory consistency regularization to enforce that adjacent processes with higher next-token generation probability maintain more consistent rewards.<n>We show that the reward model trained with the proposed regularization induces better DPO-aligned policies and achieves better best-of-N (BON) inference-time verification results.
  arXiv  Detail & Related papers  (2025-06-10T12:59:14Z)
• Offline Reinforcement Learning via Inverse Optimization [2.8037951156321372]
  We propose a novel offline Reinforcement Learning (ORL) algorithm for continuous state and action spaces.<n>To mitigate the distribution shift commonly observed in ORL problems, we employ a robust and non-causal Model Predictive Control expert.<n>Unlike the existing literature, our robust MPC expert enjoys an exact and tractable convex reformulation.
  arXiv  Detail & Related papers  (2025-02-27T12:11:44Z)
• Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization [9.618391485742968]
  Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs) We present an uncertainty-enhanced textbfPreference textbfOptimization framework to make the LLM self-evolve with reliable feedback. Our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization.
  arXiv  Detail & Related papers  (2024-09-17T14:05:58Z)

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.