Qinyu Luo
Scholar

Qinyu Luo

Google Scholar ID: ipMWfycAAAAJ
Johns Hopkins University; THUNLP
LLM-driven AgentsMuti-Agent SystemMultimodality and Real world sensing
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
137
 
H-index
5
 
i10-index
3
 
Publications
7
 
Co-authors
0
 
Contact
Emailqinyu_luo@163.comCVOpen ↗GitHubOpen ↗
Publications
7 items
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
2026
Cited
0
Test-Time Deep Thinking to Explore Implicit Rules
2026
Cited
0
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
2026
Cited
0
Current Agents Fail to Leverage World Model as Tool for Foresight
arXiv.org · 2026
Cited
3
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
2025
Cited
0
EscapeBench: Pushing Language Models to Think Outside the Box
arXiv.org · 2024
Cited
3
Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
arXiv.org · 2024
Cited
1
Resume
Academic Achievements
  • For the latest publications information, please refer to Google Scholar.
Research Experience
  • Involved in multiple research projects including open-source projects like RepoAgent and Luotuo-QA. For a comprehensive overview of research experience and project history, please refer to the Resume section.
Education
  • 1. Master's degree, Computer Science and Engineering Management, Johns Hopkins University
  • 2. Member of THUNLP, Tsinghua University
Background
  • Research interests: LLM-driven Agents, Multi-Agent System, Agentic Tool Learning, Multimodality Reasoning. Currently a member of THUNLP at Tsinghua University and pursuing a master’s degree in Computer Science and Engineering Management at Johns Hopkins University.
Miscellany
  • Aside from academic pursuits, passionate about sharing practical experience and perspectives. Delivered lectures and speeches in public settings. Plans to create tutorials on open-source platforms.