Scholar
Xiangyuan Xue
Google Scholar ID: ku1QbowAAAAJ
The Chinese University of Hong Kong
Citations & Impact
Citations
36
H-index
3
i10-index
1
Publications
5
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- 1. CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
- 2. Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
- 3. The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
- 4. Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI
- 5. ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks (EMNLP 2025)
- 6. ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems (CVPR 2025)
Research Experience
- Interned at Shanghai Artificial Intelligence Laboratory under the supervision of Dr. Lei Bai in May 2024.
Education
- Bachelor's degree: Honor Class of Artificial Intelligence at Shanghai Jiao Tong University; PhD: Multimedia Laboratory at The Chinese University of Hong Kong, supervised by Prof. Wanli Ouyang.
Background
- Research interests: Large Language Models, Multi-agent Systems, and Reinforcement Learning. Currently a PhD student at the Multimedia Laboratory of The Chinese University of Hong Kong.
