让大模型先反向思考再正向规划，提升复杂任务求解成功率。
Thinking Forward and Backward: Effective Backward Planning with Large Language Models
- 反向翻转问题后，用正向规划避开模型的反向思维偏差。
- 在三个任务中，结合双向规划使成功率提升4%至24%。
- 适合需要多步推理与路径探索的任务，如智能体规划与逻辑谜题。
大语言模型（LLMs）展现出卓越的推理与规划能力。以往研究多采用从初始状态到目标状态的正向推理，但许多规划问题存在固有不对称性：从目标反向规划往往更简单，例如当瓶颈接近目标时。我们发现这一现象同样存在于大模型规划中：单向规划的表现与该方向的规划复杂度高度相关。然而实验也揭示了系统性偏差导致反向规划表现不佳。基于此，我们提出一种反向规划算法：先将问题反转，再在反转后的问题上进行正向规划。该方法有效规避了反向偏差，生成更多样化的候选方案，并利用正反向规划的不对称性。在三个规划领域中，结合双向规划并引入自验证机制，整体规划成功率提升4%至24%。
原文摘要 · Abstract (English)
Large language models (LLMs) have exhibited remarkable reasoning and planning capabilities. Most prior work in this area has used LLMs to reason through steps from an initial to a goal state or criterion, thereby effectively reasoning in a forward direction. Nonetheless, many planning problems exhibit an inherent asymmetry such that planning backward from the goal is significantly easier -- for example, if there are bottlenecks close to the goal. We take inspiration from this observation and demonstrate that this bias holds for LLM planning as well: planning performance in one direction correlates with the planning complexity of the problem in that direction. However, our experiments also reveal systematic biases which lead to poor planning in the backward direction. With this knowledge, we propose a backward planning algorithm for LLMs that first flips the problem and then plans forward in the flipped problem. This helps avoid the backward bias, generate more diverse candidate plans, and exploit asymmetries between the forward and backward directions in planning problems -- we find that combining planning in both directions with self-verification improves the overall planning success rates by 4-24% in three planning domains.
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。