arXiv cs.CV
· Papers
Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning
arXiv:2607.02490v1 Announce Type: cross Abstract: Large vision-language models can reason over multimodal inputs by generating textual chains of thought (CoT). A key capability exhibited in CoT reasoning is self-reflection: revisiting earlier decisions and correcting previous errors. However, existing LVLMs often fail