根据推理难度动态调整策略，提升大模型测试时适应效率。
DiSCTT: Consensus-Guided Self-Curriculum for Efficient Test-Time Adaptation in Reasoning
- 基于多个推理路径的一致性估计不确定性，区分难易样本
- 高一致性样本用多数解作伪标签微调，低一致性样本用多样性约束强化学习
- 在数学与通用推理任务上精度更高、训练更快更稳定
测试时适应为无需额外标注即可提升大语言模型推理性能提供了新路径，但现有方法对所有输入采用统一优化目标，导致在异质推理问题上效率低或不稳定。本文提出DiSCTT，一种基于共识引导的自适应课程框架，通过采样推理轨迹间的一致性来估计实例级认知不确定性，动态分配优化策略：高一致性的输入采用以多数一致解为伪标签的监督微调；低一致性的输入则通过包含共识正则化的强化学习目标，鼓励相关性下的多样性。在广泛的数学与通用推理基准测试中，DiSCTT持续优于强基线，实现更高准确率、更低方差，并显著减少计算开销与实际训练时间。结果表明，显式考虑实例难度与不确定性，可实现更稳定、高效、有效的推理模型测试时适应。
原文摘要 · Abstract (English)
Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to inefficient or unstable adaptation on heterogeneous reasoning problems. We propose DiSCTT, a difficulty-aware, consensus-guided self-curriculum framework that dynamically allocates test-time optimization strategies based on instance-level epistemic uncertainty estimated from agreement among sampled reasoning trajectories. Inputs with high consensus are consolidated via supervised fine-tuning using majority-agreed solutions as pseudo-labels, while low-consensus inputs are optimized via reinforcement learning with a consensus-regularized objective that encourages diversity under relevance constraints. Across a broad suite of mathematical and general reasoning benchmarks, DiSCTT consistently outperforms strong test-time adaptation baselines, achieving higher accuracy with reduced variance and substantially lower computation and wall-clock training times. These results demonstrate that explicitly accounting for instance difficulty and uncertainty enables more stable, efficient, and effective test-time adaptation for reasoning models.
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。