Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Hao, Karnik, Sathwik, Lim, Bea, Bansal, Somil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914508610469888
author Wang, Hao
Karnik, Sathwik
Lim, Bea
Bansal, Somil
author_facet Wang, Hao
Karnik, Sathwik
Lim, Bea
Bansal, Somil
contents Large Language Models (LLMs) and Vision Language Models (VLMs) have become popular tools for embodied high-level planning. However, their deployment in black-box settings often leads to unpredictable or costly errors. To harness their capabilities more reliably in robotic systems, we empirically investigate practical strategies for integrating language models as closed-loop planners. Concretely, we study how the control horizon and warm-starting impact the performance of language model-based planners. We design and conduct controlled experiments to extract actionable insights, providing recommendations that can help improve the performance and robustness of language model-based embodied planning. The full implementation and experiments are available on the project website
format Preprint
id arxiv_https___arxiv_org_abs_2511_07410
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks
Wang, Hao
Karnik, Sathwik
Lim, Bea
Bansal, Somil
Robotics
Artificial Intelligence
Large Language Models (LLMs) and Vision Language Models (VLMs) have become popular tools for embodied high-level planning. However, their deployment in black-box settings often leads to unpredictable or costly errors. To harness their capabilities more reliably in robotic systems, we empirically investigate practical strategies for integrating language models as closed-loop planners. Concretely, we study how the control horizon and warm-starting impact the performance of language model-based planners. We design and conduct controlled experiments to extract actionable insights, providing recommendations that can help improve the performance and robustness of language model-based embodied planning. The full implementation and experiments are available on the project website
title Using Language Models as Closed-Loop High-Level Planners for Robotics Applications: A Brief Overview and Benchmarks
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2511.07410