Modeled on Berkeley’s LLM Agents course

LLM Agents:从推理到智能体系统

LLM Agents: From Reasoning to Agentic Systems

Along the 12-lecture skeleton of Berkeley's LLM Agents course — reasoning, frameworks, applications and safety, all hands-on

5 labs15 AI-mentored sessions~8 hoursBilingual · EN / 中
Start learning →

About this course

The general-education course for the age of commanding agents: why LLMs reason, where
agents came from, how multi-agent frameworks and compound AI systems work, how agents land
in software, enterprise workflows and robotics, and how to measure capability and safety.
It follows the 12-lecture skeleton of Berkeley's renowned LLM Agents course (Fall 2024),
with every session rewritten as original hands-on teaching for the online sandbox.

What you'll learn

  • Explain what each LLM reasoning technique (CoT, self-consistency, least-to-most) solves and when it fails
  • Trace the lineage of ReAct and the agent paradigm; run the reason-act-observe loop yourself
  • Compare multi-agent frameworks and compound AI systems (conversational collaboration, declarative optimization)
  • Explain how agents land in software development, enterprise workflows and robotics — and the bottlenecks
  • Assess agents through capability evals and responsible scaling; explain injection risks and defenses

Syllabus

1Foundations: Reasoning & a Brief History of Agents2 sessions
  • 1LLM Reasoning: From Direct Answers to Chains of Thought30 minStart →
  • 2A Brief History of LLM Agents30 minStart →
2Frameworks: Multi-Agent & Compound AI Systems3 sessions
  • 1Agentic Frameworks: Conversation as Collaboration30 minStart →
  • 2Enterprise GenAI: Key Components of Successful Agents30 minStart →
  • 3Compound AI Systems: Programs, Not Prompts30 minStart →
3Applications: Code, Workflows & Embodiment4 sessions
  • 1Agents for Software Development30 minStart →
  • 2AI Agents for Enterprise Workflows30 minStart →
  • 3Neural + Symbolic: Teaching Models to Plan30 minStart →
  • 4A Blueprint for Generalist Robotics30 minStart →
4Ecosystem & Safety: Openness, Evals & Trust3 sessions
  • 1Open Source & Open Science in the Foundation-Model Era30 minStart →
  • 2Measuring Agent Capabilities & Responsible Scaling30 minStart →
  • 3Safe & Trustworthy AI Agents30 minStart →
5Build an Agent: Tool-Calling, RAG & an Eval Harness3 sessions
  • 1Build a Tool-Calling Agent: The Perceive–Think–Act Loop30 minStart →
  • 2Build a RAG Agent: Retrieval-Augmented Generation30 minStart →
  • 3Build an Eval Harness: Task Success & Trajectory Scoring30 minStart →

Same series · 世界名校知名实验室系列

Flagship University Lab Series

Modeled on Stanford / MIT / Berkeley syllabi — learn from scratch with a mentor Agent guiding you in real time.