Essays on LLMs and Agents:

1. **LLM Inference-Time Computing: Enhancing the Reasoning Capabilities of LLMs (2025-02-18)**
2. **Reinforcement Learning and LLM Post-Training: How the LLMs Gain Reasoning Capabilities? (2025-02-02)**
3. **Agents in the Era of Large Language Models: A Systematic Overview (I) (2025-01-17)**
4. **Agents in the Era of Large Language Models: A Systematic Overview (II) (2025-01-25)**
5. **Opportunities in Agents after GPT-4 (2023-11-15)**
6. **The Scale Advantage of ChatGPT: Reflections on “The Bitter Lesson” (2023-02-05)**

About Me:

I hold a Ph.D. in Mathematics and Electrical Engineering from Caltech and have over 15 years of experience in AI, machine learning, automatic control, and cloud computing. My career is driven by a passion for transforming cutting-edge research into scalable, user-centric solutions that address real-world challenges. Recently, I led an AI incubation and acceleration program designed to enhance organizations' AI capabilities and fast-track their LLM projects, by delivering comprehensive services based on a robust LLM application platform, including LLM talent training, project coaching, application co-development. My current interests encompass reinforcement learning (RL), automatic control theory and its applications, LLM post-training, inference-time computation, reasoning capabilities, safety and alignment, retrieval-augmented generation (RAG), agents, and their applications.