LLM Agents
Long-horizon tasks, planning, memory, tool use and decision making.
WANG CHUANG LAB
AI · Agents ·Systems
Exploring LLM agents, long-horizon planning, reliability and AI systems engineering. This is where I document my research, projects, experiments and technical notes.
01 / Research
What I'm exploring
Agent Reliability
Failure analysis, evaluation and decision mechanisms for agents.
AI Systems
Engineering reliable systems that turn model capabilities into useful products.