When using language models (LMs) to solve complex problems, humans might struggle to understand the LM-generated solutions and repair the flawed ones. To assist humans in repairing them, we propose to automatically decompose complex solutions into multiple simpler pieces that correspond to specific subtasks. We introduce a novel objective for learning task decomposition, termed assistive value (AssistV), which measures the feasibility and speed for humans to repair the decomposed solution. We collect a dataset of human repair experiences on different decomposed solutions. Utilizing the collected data as in-context examples, we then learn to critique, refine, and rank decomposed solutions to improve AssistV. We validate our method under competitive programming problems: under 177 hours of human study, our method enables non-experts to solve 33.3\% more problems, speeds them up by 3.3x, and empowers them to match unassisted experts.

利用语言模型解决复杂问题时，通过将复杂解决方案自动分解为多个简单的部分以更好地帮助人类理解和修复，并提出新的任务分解目标“AssistV”，通过人类修复经验数据集改进解决方案的可行性和速度，在竞赛编程问题中验证方法，结果显示我们的方法使非专家能够解决更多问题并加快速度，并达到专家级别效果。

学习任务分解助力人工角逐编程