HuiKang Hu — accepted AI-conference papers

2026

EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization

Xinbang Dai, Zheyu Xin, Huikang Hu, Lin Ren, Rihui Jin, Guohui Xiao +3

IJCAI 2026

Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such as fast-slow thinking switching and reasoning trajectory compression, fail to make a fine-grained distinction between beneficial and redundant steps

Cited by 0 Scholar ↗

2026

TaxReasoning: Benchmarking Knowledge-Intensive Mathematical Reasoning with Evolving Tax Laws

Nan Hu, Yike Wu, Jiaye Li, HuiKang Hu, Guilin Qi, Songlin Zhai +5

AAAI 2026technical

Recent studies have explored the capabilities of large language models (LLMs) in solving knowledge-intensive mathematical reasoning problems. However, existing benchmarks predominantly involve static theorems that LLMs have encountered during pretraining, failing to assess dynamic knowledge integrat

Cited by 0 Source ↗PDF ↗Scholar ↗