提出用抽象计划指导模型生成推理步骤，解决长距离推理中的规划瓶颈。
Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation
- 将推理拆分为规划与执行，发现瓶颈在规划阶段
- 在GSM8k和ToolBench上性能优于直接微调CoT数据
- 尤其提升长距离推理泛化能力，适合复杂任务建模
大语言模型的多步推理能力在数学和工具使用等任务中至关重要。现有研究多通过微调链式思维（CoT）步骤来提升模型表现，但方法偏向经验性，未深入探索或解决根本瓶颈。本研究将CoT推理分解为规划与执行两部分，发现模型主要瓶颈在于规划而非执行。基于此，提出基于计划的训练与推理方法，通过抽象计划引导模型生成规划步骤。在数学（GSM8k）和工具使用（ToolBench）基准上进行实验，结果表明，相较于直接使用CoT数据微调，该方法更有效缓解规划瓶颈，尤其在长距离推理泛化方面表现优异。
原文摘要 · Abstract (English)
Multi-step reasoning ability of large language models is crucial in tasks such as math and tool utilization. Current researches predominantly focus on enhancing model performance in these multi-step reasoning tasks through fine-tuning with Chain-of-Thought (CoT) steps, yet these methods tend to be heuristic, without exploring nor resolving the bottleneck. In this study, we subdivide CoT reasoning into two parts: arranging and executing, and identify that the bottleneck of models mainly lies in arranging rather than executing. Based on this finding, we propose a plan-based training and reasoning method that guides models to generate arranging steps through abstract plans. We experiment on both math (GSM8k) and tool utilization (ToolBench) benchmarks. Results show that compared to fine-tuning directly with CoT data, our approach achieves a better performance on alleviating arranging bottleneck, particularly excelling in long-distance reasoning generalization.
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。