Author

Shuai Xiao

h-index 7 View on Semantic Scholar

We have 1 of 27 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.

Preprint Aug 2026

Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding

This work introduces Linearized Hierarchical Reinforcement Learning with Variance-Gated Rewards (LHRL-VGR), a novel algorithm that dynamically routes rewards - balancing goal completion and strategy adherence - based on the variance of goal achievement scores.

Xiaofeng Wang, Kakam Chong, Shuai Xiao et al. · 0 citations