Author

Feng-Xiang He

View on Semantic Scholar

2 papers indexed here

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.

#artificial intelligence May 2026

In LLM Reasoning, there is Irrationality on top of Value Misalignment

It is argued that, even when an LLM has been well aligned in (post-)training, it may still fail to maximise the aligned value in reasoning, and the utility discrepancy between a model's deployed reasoning strategy and its rational counterpart whose responses maximise utility in the steepest direction is formalised.

Kejiang Qian, Feng-Xiang He · arXiv.org · 0 citations

#artificial intelligence May 2026

PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate

Comprehensive empirical evaluations demonstrate PEAR significantly improves average accuracy over the strongest debate baselines, and theoretically characterize PEAR as an equivariant sparse router: it preserves accuracy under agent relabeling while reducing routing complexity and improving generalization.

Yang Feng, Ziwei Xu, Xia Hu et al. · arXiv.org · 0 citations