# Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models

arXiv: https://arxiv.org/abs/2305.10276 · HTML: https://mlsanity.com/paper/2305.10276/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 17 May 2023.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2203.12667/) (2022)
- [Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention](https://mlsanity.com/paper/1812.04155/) (2018)
- [SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning](https://mlsanity.com/paper/2104.05832/) (2021)
- [Transfer Learning with Synthetic Corpora for Spatial Role Labeling and Reasoning](https://mlsanity.com/paper/2210.16952/) (2022)
- [Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions](https://mlsanity.com/paper/2304.02868/) (2023)
- [Representation Learning for Grounded Spatial Reasoning](https://mlsanity.com/paper/1707.03938/) (2017)

## Built on by (most cited first, 6 of 6)

- [Break the Chain: Large Language Models Can be Shortcut Reasoners](https://mlsanity.com/paper/2406.06580/) (2024)
- [Meta Reasoning for Large Language Models](https://mlsanity.com/paper/2406.11698/) (2024)
- [Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers](https://mlsanity.com/paper/2505.01482/) (2025)
- [Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning](https://mlsanity.com/paper/2507.13362/) (2025)
- [Affordable AI Assistants with Knowledge Graph of Thoughts](https://mlsanity.com/paper/2504.02670/) (2025)
- [ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization](https://mlsanity.com/paper/2510.12063/) (2025)

## Abstract (arXiv)

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. Code and data available at: https://github.com/hanxuhu/chain-of-symbol-planning