Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning

• URL: http://arxiv.org/abs/2512.15146v2
• Date: Thu, 18 Dec 2025 02:04:53 GMT
• Title: Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning
• Authors: Weiqin Wang, Yile Wang, Kehao Chen, Hui Huang,
• Abstract summary: Test-time reinforcement learning mitigates reliance on annotated data by using majority voting results as pseudo-labels.<n>This voting strategy often induces confirmation bias and suffers from sparse rewards, limiting the overall performance.<n>We propose subgroup-specific step-wise confidence-weighted pseudo-label estimation (SCOPE) to address these issues.
• Score: 12.354777054071379
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time reinforcement learning mitigates the reliance on annotated data by using majority voting results as pseudo-labels, emerging as a complementary direction to reinforcement learning with verifiable rewards (RLVR) for improving reasoning ability of large language models (LLMs). However, this voting strategy often induces confirmation bias and suffers from sparse rewards, limiting the overall performance. In this work, we propose subgroup-specific step-wise confidence-weighted pseudo-label estimation (SCOPE), a framework integrating model confidence and dynamic subgroup partitioning to address these issues. Specifically, SCOPE integrates the proposed step-wise confidence into pseudo label deduction, prioritizing high-quality reasoning paths over simple frequency count. Furthermore, it dynamically partitions the candidate outputs pool into independent subgroups by balancing reasoning quality against exploration diversity. By deriving local consensus via repeat sampling for each sub group, SCOPE provides diverse supervision targets to encourage broader exploration. We conduct experiments across various models and benchmarks, experimental results show that SCOPE consistently outperforms recent baselines. Notably, SCOPE achieving relative improvements of 13.1% on challenging AIME 2025 and 8.1% on AMC. The code is released at https://github.com/szu-tera/SCOPE.

Related papers

• A Single Revision Step Improves Token-Efficient LLM Reasoning [3.344806691289323]
  We introduce Packet-Conditioned Revision (PACER), a training-free, inference-only framework for large language models.<n>PACER enables reasoning traces to revise their conclusions through a structured coordination step.<n>On challenging competitive math benchmarks, PACER matches or exceeds the accuracy of 256-sample majority voting.
  arXiv  Detail & Related papers  (2026-02-02T21:28:42Z)
• SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning [50.93295951454092]
  We introduce a set level diversity objective defined over sampled trajectories using kernelized similarity.<n>Our approach derives a leave-one-out marginal contribution for each sampled trajectory and integrates this objective as a plug-in advantage shaping term for policy optimization.<n>Experiments across a range of model scales demonstrate the effectiveness of our proposed algorithm, consistently outperforming strong baselines in both Pass@1 and Pass@K across various benchmarks.
  arXiv  Detail & Related papers  (2026-02-01T07:13:20Z)
• From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning [7.6602542594279335]
  We propose Reinforcement Learning with Relative Rewards to shift reward shaping from absolute scoring to relative ranking.<n>We show that RLRR yields consistent performance improvements over standard group-based baselines across reasoning benchmarks and open-ended generation tasks.
  arXiv  Detail & Related papers  (2026-01-30T15:07:06Z)
• CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation [6.356820150960838]
  We introduce two complementary approaches inspired by test-time scaling to stabilize vision-language models.<n>CASHEW is an inference-time framework that stabilizes reasoning by iteratively aggregating multiple candidate trajectories into higher-quality reasoning traces.<n>CASHEW-RL is trained using Group Sequence Policy Optimization (GSPO) with a composite reward that encourages correct answers grounded in minimal yet sufficient visual evidence.
  arXiv  Detail & Related papers  (2026-01-12T21:24:45Z)
• ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning [17.98065634130798]
  We propose the Intrinsic Confidence-Driven Group Relative Preference Optimization method (ICPO)<n>ICPO calculates a preference advantage score for each response by comparing the relative generation probabilities of multiple responses under the same input prompt.<n>We have discovered that the preference advantage score not only alleviates the issues of coarse-grained rewards and reward noise but also effectively curbs overconfident errors.
  arXiv  Detail & Related papers  (2025-11-26T03:10:15Z)
• MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources [113.33902847941941]
  Variance-Aware Sampling (VAS) is a data selection strategy guided by Variance Promotion Score (VPS)<n>We release large-scale, carefully curated resources containing 1.6M long CoT cold-start data and 15k RL QA pairs.<n> Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS.
  arXiv  Detail & Related papers  (2025-09-25T14:58:29Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning [64.46921169261852]
  RAG-Zeval is a novel end-to-end framework that formulates faithfulness and correctness evaluation as a rule-guided reasoning task.<n>Our approach trains evaluators with reinforcement learning, facilitating compact models to generate comprehensive and sound assessments.<n>Experiments demonstrate RAG-Zeval's superior performance, achieving the strongest correlation with human judgments.
  arXiv  Detail & Related papers  (2025-05-28T14:55:33Z)
• Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness [61.45587642780908]
  We propose a three-step approach for parameter-efficient fine-tuning of image-text foundation models.<n>Our method improves its two key components: minority samples identification and the robust training algorithm.<n>Our theoretical analysis shows that our PPA enhances minority group identification and is Bayes optimal for minimizing the balanced group error.
  arXiv  Detail & Related papers  (2025-03-12T15:46:12Z)
• Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification [0.0]
  This paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. We put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-25T10:10:48Z)
• Rethinking Sampling Strategies for Unsupervised Person Re-identification [59.47536050785886]
  We analyze the reasons for the performance differences between various sampling strategies under the same framework and loss function.<n>Group sampling is proposed, which gathers samples from the same class into groups.<n>Experiments on Market-1501, DukeMTMC-reID and MSMT17 show that group sampling achieves performance comparable to state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-07-07T05:39:58Z)

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.