arXiv cs.CL
· Papers
Trace, Verify, and Correct: A Training-Free Framework for Spatial Reasoning in Multimodal LLMs
arXiv:2608.04759v1 Announce Type: cross Abstract: Although Multimodal Large Language Models (MLLMs) have made substantial progress, their spatial reasoning may still produce intermediate judgments inconsistent with the input image, allowing errors to propagate through the reasoning chain and affect the final answer. Ex