Ruijie Shi — accepted AI-conference papers

2026

AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction

Ruijie Shi, Houbin Zhang, Yuecheng Han, Yuheng Wang, Jingru Fan, Runde Yang +5

ICML 2026poster

Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and control due to opaque internal workflows. While some frameworks offer explicit architectures for collaboration, many deployed agentic systems operate as black b…

Cited by 0 Source ↗Scholar ↗

2025

Multi-Agent Collaboration via Evolving Orchestration

Yufan Dang, Chen Qian, Xueheng Luo, Jingru Fan, Zihao Xie, Ruijie Shi +8

NeurIPS 2025poster

Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, most approaches rely on static organization…

Cited by 0 Source ↗code ↗Scholar ↗