← Search

Xiaoran Shang

2 accepted papers

2026

DAWN: Distributed LLM Multi-Agent Workflow Synthesis

AAAI 2026technical

Large language models (LLMs) have recently empowered multi-agent systems (MAS) to achieve remarkable advances in collaborative reasoning and complex task automation. The effectiveness of these systems fundamentally depends on the design of adaptive communication graphs—the underlying workflows that

Cited by 0SourcePDFScholar
2025

HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning

NeurIPS 2025spotlight

Robust Federated Graph Learning (FGL) provides an effective decentralized framework for training Graph Neural Networks (GNNs) in noisy-label environments. However, the subtlety of noise during training presents formidable obstacles for developing robust FGL systems. Previous robust FL approaches nei…

Cited by 0SourceScholar