activity
20212026
most citedGo Wider Instead of Deeper

3 citations · 3 across the 5 of their papers we have counts for

collaborators

6 papers

cs.AI2026

MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning

Ziyang Luo, Yan Yang, Xiangru Jian +5

Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks stop at the policy update.…

cs.SE2026

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

Yan Yang, Xiangru Jian, Ziyang Luo +7

Computer-use agents are usually improved by strengthening perception: better models for reading a screenshot and choosing where to click. Yet a screenshot is only a lossy rendering…

cs.DC2025

Reaching Agreement Among Reasoning LLM Agents

Chaoyi Ruan, Yiliang Wang, Ziji Shi +1

Multi-agent systems have extended the capability of agentic AI. Instead of single inference passes, multiple agents perform collective reasoning to derive high quality answers. How…

cs.DC2025

Cortex: Achieving Low-Latency, Cost-Efficient Remote Data Access For LLM via Semantic-Aware Knowledge Caching

Chaoyi Ruan, Chao Bi, Kaiwen Zheng +3

Large Language Model (LLM) agents tackle data-intensive tasks such as deep research and code generation. However, their effectiveness depends on frequent interactions with knowledg…

cs.DC2024

ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks

Ziji Shi, Jialin Li, Yang You

Recent advances in Generative Artificial Intelligence have fueled numerous applications, particularly those involving Generative Adversarial Networks (GANs), which are essential fo…

cs.LG20213 cited

Go Wider Instead of Deeper

Fuzhao Xue, Ziji Shi, Futao Wei +3

More transformer blocks with residual connections have recently achieved impressive results on various tasks. To achieve better performance with fewer trainable parameters, recent…