In this paper, we take the initiative to investigate the performance of LLMs on complex planning tasks that require LLMs to understand a virtual spatial environment simulated via natural language and act correspondingly in text. We propose a benchmark named Natural Language Planning and Action (Natala) composed of a set of novel tasks: Brick World, NLVR-based Manipulations, and Natural Language Navigation. We found that current popular LLMs such as ChatGPT still lack abilities in complex planning. This arises a question -- do the LLMs have a good understanding of the environments described in natural language, or maybe other alternatives such as symbolic representations are neater and hence better to be understood by LLMs? To this end, we propose a novel method called CoS (Chain-of-Symbol Prompting) that represents the complex environments with condensed symbolic spatial representations during the chained intermediate thinking steps. CoS is easy to use and does not need additional training on LLMs. Extensive experiments indicate that CoS clearly surpasses the performance of the Chain-of-Thought (CoT) Prompting in all three planning tasks with even fewer tokens used in the inputs compared with CoT on ChatGPT and InstructGPT. The performance gain is strong, by up to 60.8% accuracy (from 31.8% to 92.6%) on Brick World for ChatGPT. CoS also reduces the number of tokens in the prompt obviously, by up to 65.8% of the tokens (from 407 to 139) for the intermediate steps from demonstrations on Brick World.

翻译：本文率先研究了大型语言模型在复杂规划任务中的表现，这些任务要求 LLM 理解通过自然语言模拟的虚拟空间环境，并以文本形式做出相应行动。我们提出了一个名为自然语言规划与行动（Natala）的基准测试，包含一组新颖任务：砖块世界、基于NLVR的操作和自然语言导航。我们发现，当前流行的 LLM（如 ChatGPT）在复杂规划方面仍缺乏能力。这引发了一个问题——LLM 是否真的理解了自然语言描述的环境？或者符号表示等其他替代方案是否更简洁，因而更易被 LLM 理解？为此，我们提出了一种名为 CoS（链式符号提示）的新方法，该方法在链式中间推理步骤中用紧凑的符号空间表示来描述复杂环境。CoS 易于使用，无需对 LLM 进行额外训练。大量实验表明，在 ChatGPT 和 InstructGPT 上，与思维链（CoT）提示相比，CoS 在所有三个规划任务中的性能明显更优，且输入的令牌数更少。性能提升显著：在砖块世界任务中，ChatGPT 的准确率从 31.8% 提升至 92.6%（提升 60.8%）。CoS 还显著减少了提示中的令牌数，在砖块世界的示范中，中间步骤的令牌数从 407 降至 139（减少 65.8%）。