ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling· ThinkRetrieve：测试时增强推理路径的检索方法
Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies reveal that sequential test-time scaling often yields diminishing or even negative returns, as longer traces exhibit increased uncertainty, error compounding, and drift from the original problem. We propose ThinkRetrieve, a test-time scaling framework that augments the reasoning traces of LRMs with dynamically retrieved solved examples at each reasoning step. Given an external corpus of problems paired with step-by-step solutions, ThinkRetrieve retrieves relevant exemplars at each intermediate step and injects them directly into the thinking trace, providing the model with guidance on how to reason rather than merely what
测试时通过检索增强大型推理模型的思考过程，提升准确性。
- 核心方法
- 提出ThinkRetrieve框架，利用外部问题配对解答语料库，在每一步推理过程中动态检索并注入相关示例，为模型提供推理指导。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 解决大型推理模型在测试时由于推理路径过长导致的不确定性增加、错误累积以及偏离原问题的问题。
- 关键实验
- 实验表明，在多个推理任务上，ThinkRetrieve相比传统的测试时增强方法，性能有显著提升。
- 主要贡献
- 减少了测试时推理路径的不确定性、错误累积和偏离问题，提升了模型的推理能力和准确性。
- 意义与局限
- 该方法有效改进了大型推理模型的测试表现，但需要充足的高质量示例库支持，可能限制其在某些领域的应用。