Author

Zhining Liu

2 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.

#artificial intelligence Review Jan 2026

A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents

This survey synthesizes agentic reasoning methods into a unified roadmap bridging thought and action, and outlines open challenges and future directions, including personalization, long-horizon interaction, world modeling, scalable multi-agent training, and governance for real-world deployment.

Tian-Xin Wei, Ting-Wei Li, Zhining Liu et al. · 39 citations · ⚡6

#artificial intelligence Jan 2026

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

AdaFuse is an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation that establishes a synergistic interaction between adaptive ensembling and test-time scaling, where ensemble decisions guide targeted exploration, and the resulting diversity in turn stren...

Cheng Cui, Tianxin Wei, Ziyi Chen et al. · arXiv.org · 6 citations · ⚡1