Author

Xingjian Tao

h-index 2 View on Semantic Scholar

We have 1 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning

A staged length bonus is introduced that keeps reasoning length within a controlled range without simply encouraging brevity in multi-view spatial reasoning, and improves accuracy over vanilla GRPO while reducing average response length.

Xingjian Tao, Yiwei Wang, Yujun Cai et al. · arXiv.org · 0 citations