Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xingyu Zhu

Xingyu Zhu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2NLP×1

Frequent co-authors

Ziyang Cai1×
Yihe Dong1×
Yinghui He1×
Sanjeev Arora1×
Yi Ding1×
Zijie Xuan1×

Research Timeline

2026
TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

T^2MLR: Transformer with Temporal Middle-Layer Recurrence

The paper introduces Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transformers-based latent reasoning architecture that enables abstract intermediate computation to persist across decoding steps with little inference overhead.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIEmpiricalRecentJul 16, 2026

T^2MLR: Transformer with Temporal Middle-Layer Recurrence

Ziyang Cai, Xingyu Zhu, Yihe Dong, Yinghui He +1 more

The paper introduces Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transformers-based latent reasoning architecture that enables abstract intermediate computation to persist across dec…

View →
cs.AIRecentMay 27, 2026

TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems

Yi Ding, Zijie Xuan, Haowei Zhou, Zhenyu Ju +5 more

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

View →