作者：Qingmiao Liang, Jiatao Zhang, Runxin Zou, Yufan Song, Wei Song, Yuhua Zheng
来源：arXiv cs.RO（机器人）
正文
Computer Science > Robotics
arXiv:2610.35686v1 (cs)
[Submitted on 26 Oct 2026 (this version), latest version 27 Oct 2026 (v2)]
Title:FISRF: Flexible Instructional Scaffolding Reflection Framework for Robotics Task Planning with Large Language Model
Authors:Qingmiao Liang, Jiatao Zhang, Runxin Zou, Yufan Song, Wei Song, Yuhua Zheng
View a PDF of the paper titled FISRF: Flexible Instructional Scaffolding Reflection Framework for Robotics Task Planning with Large Language Model, by Qingmiao Liang and Jiatao Zhang and Runxin Zou and Yufan Song and Wei Song and Yuhua Zheng
View PDF
HTML (experimental)
Abstract:Large Language Models (LLMs) are widely adopted for reflective error correction in task planning; however, existing approaches primarily rely on autonomous exploration, rendering them prone to accumulating erroneous experiences during early interactions with new environments. To address this limitation, we propose the Flexible Instructional Scaffolding Reflection Framework (FISRF), an agent–mentor architecture that estimates the robot’s Zone of Proximal Development (ZPD) in task planning and adaptively selects reflection strategies and mentor guidance, thereby facilitating the accumulation of effective error-correction experience. Experiments in ALFWorld and on real-world robotic platforms demonstrate that FISRF reduces the average number of error-correction rounds by 37% and redundant reasoning by 25.1%, while improving the overall task success rate by 8%. Project webpage : this https URL
Subjects:
Robotics (cs.RO)
Cite as:
arXiv:2610.35686 [cs.RO]
(or
arXiv:2610.35686v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.35686
Focus to learn more
arXiv-issued DOI via DataCite
主题
机器人
由「前沿雷达」于 2026-10-27 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。
评论
加载中…