Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation
Yu Zhong, Zihao Zhang, Rui Zhang, Lingdong Huang, Haihan Gao, Shuo Wang, Da Li, Ruijian Han
Abstract
Vision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions. Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities. Despite their strengths, a substantial gap in task completion performance persists between LLM-based approaches and domain experts, as LLMs inherently struggle to comprehend real-world spatial correlations precisely; additionally, LLM inference can make the decision-making process considerably inefficient. To address these issues, we propose a novel dual-process thinking framework dubbed R3, integrating LLMs
BibTeX
@inproceedings{aaai2026_runruminateandre,
title = {Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation},
author = {Yu Zhong and Zihao Zhang and Rui Zhang and Lingdong Huang and Haihan Gao and Shuo Wang and Da Li and Ruijian Han and Jiaming Guo and Shaohui Peng and Di Huang and Yunji Chen},
booktitle = {AAAI 2026},
year = {2026}
}