CritICL：从小语言模型失败模式中实现推理时的弱到强泛化

摘要

近期，推理时扩展（inference-time scaling）方面的进展显著提升了大语言模型（LLMs）的推理性能。然而，这些方法通常依赖于重复生成或外部验证。为解决这一局限，我们提出了CritICL，一种新颖的推理时框架，能够在保持高效率的同时增强推理能力。我们的关键洞察在于，同一模型家族内，LLM的失败模式在不同规模下表现出结构化模式。CritICL不将失败视为不良输出，而是将其作为指导信息来源加以利用。具体而言，我们利用从较弱模型中获取的失败模式，通过基于批判的上下文示例将其融入推理过程。我们提出了两种变体：CritICL-dynamic，能够自适应地预测特定输入的失败模式并检索批判；以及CritICL-static，利用全局失败模式画像提供稳定的指导。实验结果表明，CritICL持续优于标准上下文学习，并以显著更少的生成次数和更低的token开销达到与测试时扩展方法相当或更优的性能。代码可在以下网址获取：https://github.com/umwyf/CRITICL

English

Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods typically rely on repeated generation or external verification. To address this limitation, we introduce CritICL, a novel inference-time framework that improves reasoning while maintaining high efficiency. Our key insight is that LLM failure modes exhibit structured patterns across model scales within the same family. Instead of treating failures as undesirable outputs, CritICL leverages them as a source of guidance. Specifically, we utilize failure modes derived from weaker models and incorporate them into inference through critique-based in-context examples. We propose two variants: CritICL-dynamic, which adaptively predicts input-specific failure modes and retrieves critiques, and CritICL-static, which uses a global failure mode profile to provide stable guidance. Experimental results show that CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods, while requiring significantly fewer generations and lower token cost. Code available at: https://github.com/umwyf/CRITICL