Papers
arxiv:2406.15275

Cognitive Map for Language Models: Optimal Planning via Verbally Representing the World Model

Published on Jun 21
· Submitted by doyoungkim on Jun 24
Authors:
,

Abstract

Language models have demonstrated impressive capabilities across various natural language processing tasks, yet they struggle with planning tasks requiring multi-step simulations. Inspired by human cognitive processes, this paper investigates the optimal planning power of language models that can construct a cognitive map of a given environment. Our experiments demonstrate that cognitive map significantly enhances the performance of both optimal and reachable planning generation ability in the Gridworld path planning task. We observe that our method showcases two key characteristics similar to human cognition: generalization of its planning ability to extrapolated environments and rapid adaptation with limited training data. We hope our findings in the Gridworld task provide insights into modeling human cognitive processes in language models, potentially leading to the development of more advanced and robust systems that better resemble human cognition.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2406.15275 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2406.15275 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2406.15275 in a Space README.md to link it from this page.

Collections including this paper 1