Wendi Yu

most citedAutonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics

1 citations · 1 across the 4 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

When Do Multi-Agent Systems Help? An Information Bottleneck Perspective

Wendi Yu, Lianhao Zhou, Xiangjue Dong +6

LLM powered multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, their advantages over single-agent systems (SAS) remain unclear, with perform…

cs.LG2026

Spin-Weighted Spherical Harmonics Enable Complete and Scalable $E (3)$ -Equivariant Networks

Chenxing Liang, Yuchao Lin, Andrii Kryvenko +5

$E (3)$ -equivariant networks are promising for 3D atomistic system modeling, yet their scalability is limited by the $O (L^{6})$ complexity of the Clebsch-Gordan Tensor Produc…

When Do Multi-Agent Systems Help? An Information Bottleneck Perspective

Spin-Weighted Spherical Harmonics Enable Complete and Scalable E(3)-Equivariant Networks

Spin-Weighted Spherical Harmonics Enable Complete and Scalable $E (3)$ -Equivariant Networks