This paper presents a two-stage training framework enhancing LLMs' visual reasoning for maze navigation, achieving 93% accuracy through Supervised Fine-Tuning and Group Relative Policy Optimization.
https://arxiv.org/abs//2502.14669
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers