Author

Ziyang Luo

3 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.

Preprint Aug 2026

You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model

A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates. This paper consolidates two research lines that address these on the same residual stream: a conditi...

Ziyang Luo, Zhong-Yao Chu, Xin-Jie He et al. · 0 citations

#artificial intelligence Preprint Oct 2026

From Evidence to Action: How Tool-Using Agents Fail

Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and dependent workflows....

Hongzhan Lin, Shi-Dong Cao, Ziyang Luo et al. · 0 citations

#natural language process... Preprint Sep 2026

Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models

Reinforcement learning with binary correctness rewards trains correctness, not calibrated confidence. The confidence that reasoning models verbalize is systematically overconfident, and the problem is not merely one of scale: verbalized confidence tracks how willing a model is to commit to an answer, not how likely the...

Ya-Dong Xi, Rong-Sheng Zhang, Tang-Jie Lv et al. · 0 citations