根据题目难易动态分配计算资源，提升大模型推理效率。
Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning
- 基于输出概率估计每题难度，无额外计算成本
- 在六项测试中平均准确率提升最多3%，个别任务达5%
- 适合资源有限的推理场景，无需额外模型或调用
多轮采样能提升语言模型推理效果，但均匀分配计算资源效率低：简单问题过度采样，难题仍采样不足。我们提出不确定性感知预算分配（UAB），一种凹型整数优化框架，基于每个问题的不确定性重新分配固定采样预算，且不增加额外推理开销。第一阶段，每个问题生成一次，其平均负对数似然（ANLL）直接从输出概率中提取，作为难度信号，同时该生成结果参与最终投票。第二阶段，剩余预算通过边际贪心算法分配，精确求解凹型覆盖最大化代理目标：不确定性高的问题获得更多采样，信心高的问题则减少追加样本。在涵盖1.5B至27B参数的六种开源与黑盒模型，以及数学、逻辑和偏好任务的五个推理基准上评估，UAB相比基线平均准确率最高提升3%，单个基准最高提升5%，在低资源环境下增益最显著，且无需辅助模型或额外大模型调用。代码已公开于https://github.com/manhitv/UAB。
原文摘要 · Abstract (English)
Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard questions remain under-explored. We propose Uncertainty-Aware Budget Allocation (UAB), a concave integer optimization framework that reallocates a fixed sampling budget based on per-question uncertainty estimated at no additional inference cost. In Phase 1, every question receives one generation; its average negative log-likelihood (ANLL), extracted directly from output log-probabilities, serves as a difficulty signal while the generation contributes to the final vote. In Phase 2, the remaining budget is allocated by a marginal-greedy algorithm that solves a concave coverage-maximization surrogate exactly: uncertain questions receive more sampling budget while confident questions receive fewer additional samples. Evaluated on six open-weight and black-box models spanning 1.5B to 27B parameters and five reasoning benchmarks covering math, logic, and preference tasks, UAB outperforms baselines by up to +3% in average accuracy and up to +5% on individual benchmarks, with the largest gains in low-resource settings, requiring no auxiliary model or additional LLM call. Code is publicly available at https://github.com/manhitv/UAB.
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。