UvA-DARE (Digital Academic Repository) Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Baohao Liao, Yuhui Xu, Han-Ze Dong et al.
· 0 citations
We have 3 of 9 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.
LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
LiveMathematicianBench is presented, a dynamic multiple-choice benchmark for research-level mathematical reasoning built from recent arXiv papers published after model training cutoffs, and introduces a thirteen-category logical taxonomy of theorem types, enabling fine-grained evaluation across reasoning forms.
Lin-Yang He, Qi-Yao Yu, Han-Ze Dong et al.
· 1 citation
· ⚡1
Jul 2026
Multi-Turn On-Policy Distillation with Prefix Replay
ReOPD turns expensive agent-environment interaction into a reusable offline resource, enabling scalable distillation across tools, tasks, and environments and preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4$\times faster per rollout than OPD.
Baohao Liao, Hanze Dong, C. Monz et al.
· arXiv.org · 7 citations
· ⚡1