DF

Dianxuan Fu

0009-0004-7127-6992

physics.opticscs.AIcs.MAcs.CRcs.NI

On Valency

published · living versions

W_4fxtemgq·v1 · currentpublished

EvoTeam: Multi-Agent Collaboration via Evolving Teams

with Qinuo Cao, Xin He, Lizhi Zhang, Zhaoqing Xing +5

1 version

Preprints & journals

4 papers in the corpus · 2025–2026

SkillPoison: Progressive Skill Poisoning via Successful Experiences2610.07645v1 · Lizhi Zhang, Xin He, Dianxuan Fu et al.2026 · 0 citationsarXiv

First Demonstration of Multi-Agent LLM System for Million-Scale Optical Link Management in Global Production AIDCs2608.23145v1 · Jingyi Su, Yihao Zhang, Dianxuan Fu et al.2026 · 0 citationsarXiv

CBA: Communication-Bound-Aware Cross-Domain Resource Assignment for Pipeline-Parallel Distributed LLM Training in Dynamic Multi-DC Optical Networks2512.20080v1 · Dianxuan Fu, Xiaomin Liu, Yihao Zhang et al.2025 · 0 citationsarXiv

First Field-Trial Demonstration of L4 Autonomous Optical Network for Distributed AI Training Communication: An LLM-Powered Multi-AI-Agent Solution2504.01234v2 · Yihao Zhang, Qizhi Qiu, Xiaomin Liu et al.2025 · 5 citationsarXiv

Career total: 11 works. 4 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.