Andrew Zhao
andrewzh
AI & ML interests
Reinforcement Learning, Agents
Recent Activity
authored
a paper
2 days ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
authored
a paper
2 days ago
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
authored
a paper
2 days ago
Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
Organizations
