根据题目难易自动拆解推理步骤，提升大模型准确率并节省计算资源。
Complexity Agnostic Recursive Decomposition of Thoughts
- 先预测题目复杂度，再动态拆解为多步推理，每步分配适量思考内容。
- 在GSM8K上准确率达81.4%~89.2%，耗 token 数减少1.88至2.40倍。
- 适合需要高效高精度推理的场景，尤其对资源有限的部署有帮助。
大语言模型在多步推理中常因固定策略而失败，忽视问题本身的难度差异。本文提出CARD（Complexity Agnostic Recursive Decomposition）框架，通过预判问题复杂度来自适应地调整分解方式。系统包含一个0.6B参数的Qwen模型MRCE（Multi-dimensional Reasoning Complexity Estimator），可从题干文本中预测30个细粒度特征；采用两阶段递归求解：(1) 根据任务特征将问题分解为K步；(2) 通过递归MRCE分析，为每步分配1、5-9或10条思考内容的预算。在Qwen3-0.6B、DeepSeek-R1-Distill-Qwen-1.5B、Qwen3-1.7B三个推理模型上评估，CARD在GSM8K上准确率达81.4%~89.2%，token消耗减少1.88至2.40倍；在MATH-500上准确率达75.1%~86.8%，耗时减少1.71至5.74倍。结果表明，预先估计复杂度能同时提升准确率与效率。
原文摘要 · Abstract (English)
Large language models often fail on multi-step reasoning due to fixed reasoning strategies that ignore problem specific difficulty. We introduce CARD (Complexity Agnostic Recursive Decomposition), a framework that predicts problem complexity before generation and adapts decomposition accordingly. Our system comprises MRCE (Multi-dimensional Reasoning Complexity Estimator), a 0.6B Qwen model predicting 30 fine-grained features from question text and a two-stage recursive solver: (1) hierarchical decomposition into K steps based on task profile and (2) per-step thought budget allocation (1, 5-9, or 10 thoughts) via recursive MRCE profiling. Evaluated on three reasoning models (Qwen3-0.6B, DeepSeek-R1-Distill-Qwen-1.5B, Qwen3-1.7B), CARD achieves 81.4% to 89.2% accuracy on GSM8K while reducing token cost by 1.88x to 2.40x compared to fixed decomposition baselines. On MATH-500, CARD reaches 75.1 to 86.8% accuracy using 1.71x to 5.74x fewer tokens. Our results demonstrate that preemptive complexity estimation enables both higher accuracy and significant efficiency gains.
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。