Author

Hong-Juan Pei

h-index 0 View on Semantic Scholar

We have 2 of 2 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 Aug 2026

Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination

COVE is presented, a unified agent self-evolution framework that combines harness-based and parameter-based learning through task-aware routing, stage-aware scheduling, and knowledge optimization, and shows that COVE outperforms single-channel evolution strategies.

T. Ji, Zhenya Huang, Jiayu Liu et al. · 0 citations

Cross Domain Test Time Scaling: Scale Knowledge and Reasoning on Cross Domains

Cross-Domain TTS is proposed, a novel framework that enables task-tailored scaling in broader domains and achieves an improvement of up to 17% in pass@1 accuracy while reducing inference latency and saving up to 30% in token consumption.

Minxi Yan, Yihua Shao, Yanling Pan et al. · 0 citations