About
Recent Research Interests
News
- Excited to release our PettingLLMs for multi-agent reinforcement learning training framework — check it out and give it a try! 🚀
- Thrilled to share our new preprint on on-policy reinforcement learning for multi-agent systems! Check out the blog for more details. 📄
- Completed three-month research internship at Intel AI Team.
- One first-author paper accepted to DAC 2025.
- One first-author paper accepted to NeurIPS 2024.
- One first-author paper accepted to DAC 2024.
First Author Publications (Full List on Google Scholar)
Stronger Together: On-Policy Reinforcement Learning with Multi-Agent Systems
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
Accepted by NeurIPS 2024,
CCF A
MAGE: A Multi-Agent Engine for Automated RTL Code Generation
Accepted by DAC 2025, CCF A
3D-Carbon: An Analytical Carbon Modeling Tool for 3D and 2.5D Integrated Circuits
Accepted by DAC 2024, CCF A
Selected Collaborated Publications and Manusripts
1. OrcaLoca: An LLM Agent Framework for Software Issue Localization
2. Instant-RAG: Enabling Instant Retrieval-Augmented Generation in LLMs via In-Storage Processing
Top