Computer Science · Artificial Intelligence
Zheng Luo
Master's student at USC working on large language models, agentic systems, reinforcement learning, and explicit, explainable AI.
- LLM
- Agentic Systems
- Reinforcement Learning
- Rule-Based AI
- Explainable AI
Papers Published or Under Review
- TreeMPO: Fine-Grained Credit Assignment for LLM Training via Token-Level Trajectory Branching
- Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
- Street-Level Competitive Ride-Hailing with Fixed-Rival Defensive PSRO
- Fairness or Fluency? An Investigation into Language Bias of Pairwise LLM-as-a-Judge
- When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
- SkiLT: What Agent Reinforcement Learning Actually Learns from a Latent Skill Library
- Predicting the Transfer Intentions of Specialist Nurses through Machine Learning