用动态分组和置信度加权，让测试时强化学习更准更可靠。
Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning
- 按推理质量动态分组，用置信度替代简单投票
- 在AIME 2025上提升13.1%，AMC上提升8.1%
- 适合需要高可靠性奖励信号的复杂推理任务
测试时强化学习通过多数投票生成伪标签，减少对标注数据的依赖，成为提升推理能力的补充方向。然而，该策略常引发确认偏差且奖励稀疏，制约性能。本文提出子组特定的逐步置信度加权伪标签估计框架（SCOPE），融合模型置信度与动态子组划分以解决此问题。具体地，SCOPE将逐步置信度引入伪标签估计，优先选择高质量推理路径而非仅计数频率；同时，通过平衡推理质量与探索多样性，动态划分候选输出池为独立子组。每个子组内通过重复采样获取局部共识，提供多样化监督信号以促进广泛探索。在多个模型与基准上的实验表明，SCOPE持续优于近期基线，在挑战性AIME 2025上实现13.1%的相对提升，在AMC上达8.1%。代码已公开于https://github.com/szu-tera/SCOPE。
原文摘要 · Abstract (English)
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. 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 estimation, 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。