Author

Zhiyuan Li

h-index 4 View on Semantic Scholar

We have 3 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.

Preprint Oct 2026

Answer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization

An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finalization cue. On 100 fresh, independently audited GSM8K test questions per model, it improves delivered endpoint accuracy over first-box stopping by 8.0 p...

Yu-Peng Chang, Lin-Yuan Gao, Zhiyuan Li et al. · 0 citations

#artificial intelligence Preprint Sep 2026

More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models

Direct-decision models enable efficient classification and evaluation by selecting from predefined candidates, but their reliability depends on more than prediction accuracy. Across 40 datasets and nine models from the JEV, KEV, and StartLux Decision families, we identify a systematic tendency to underuse ordinal ratin...

Tian-Xiang Gao, Jin-Zhe Li, Zhiyuan Li et al. · 3 citations

Preprint Aug 2026

CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval

CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before retrieval, is proposed, position edge-confidence calibration as an effective route to compact and executable skill retrieval at scale.

Zhiyuan Li, Lin-Yuan Gao, Xue-Chun Ding et al. · 3 citations