Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-Temporal Reasoning
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Large Language Models, Spatial-Temporal Reasoning, Path Planning
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: The paper proposed a benchmark and evaluated LLMs' spatial-temporal reasoning capability
Abstract: Large language models (LLMs) have achieved remarkable success across a wide spectrum of tasks; however, they still face limitations in scenarios that demand long-term planning and spatial reasoning. To facilitate this line of research, in this work, we propose a new benchmark, termed $\textbf{P}$ath $\textbf{P}$lanning from $\textbf{N}$atural $\textbf{L}$anguage ($\textbf{PPNL}$). Our benchmark evaluates LLMs’ spatial-temporal reasoning by formulating “path planning” tasks that require an LLM to navigate to target locations while avoiding obstacles and adhering to constraints. Leveraging this benchmark, we systematically investigate LLMs including GPT-4 via different few-shot prompting methodologies and BART and T5 of various sizes via fine-tuning. Our experimental results show the promise of few-shot GPT-4 in spatial reasoning, when it is prompted to reason and act interleavedly, although it still fails to make long-term temporal reasoning. In contrast, while fine-tuned LLMs achieved impressive results on in-distribution reasoning tasks, they struggled to generalize to larger environments or environments with more obstacles.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6535
Loading