llm_learn

外观

L00 · 课程参考资料 ​

本页按 CS329Z Fall 2026 的课程顺序汇总各讲涉及的讲义、视频、代码与延伸阅读。每讲页面仍保留与本讲直接相关的资料入口。

资料索引

按课程顺序整理讲义、视频、代码与延伸阅读；每一项都保留在对应讲次下。

57 条资料 · 17 讲 · 57 次关联

01

Introduction — What Are Agentic Systems?

4 条资料

讲义 / SlidesLecture 1 slides延伸阅读技术文章Zaharia et al. "The Shift from Models to Compound AI Systems." BAIR Blog (2024).官方课程阅读技术文章Ng. "Agentic Design Patterns Part 1: Four AI Agent Strategies…" The Batch (2024).官方补充阅读论文Si et al. "Towards Execution-Grounded Automated AI Research." arXiv (2026).官方补充阅读
02

LLMs for Builders

3 条资料

讲义 / SlidesLecture 2 slides延伸阅读技术文章Schluntz & Zhang. "Building Effective Agents." Anthropic (2024).官方课程阅读技术文章Rajasekaran et al. "Effective Context Engineering for AI Agents." Anthropic (2025).官方补充阅读
03

Retrieval-Augmented Generation (RAG)

3 条资料

讲义 / SlidesLecture 3 slides延伸阅读论文Lewis et al. "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks." NeurIPS (2020).官方课程阅读论文Khattab & Zaharia. "ColBERT: Efficient and Effective Passage Search via Late Interaction over BERT." SIGIR (2020).官方补充阅读
04

Tool Use & Function Calling

2 条资料

讲义 / SlidesSlides官方课程页面新增资料；来源：https://cs329z.stanford.edu/；核对：2026-10-16。文档Model Context Protocol Specification. The Linux Foundation (2025).官方课程阅读
05

Frameworks & Orchestration

2 条资料

讲义 / SlidesSlides官方课程页面新增资料；来源：https://cs329z.stanford.edu/；核对：2026-10-16。论文Khattab et al. "DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines." ICLR (2024).官方课程阅读
06

Agent Design Patterns & Scaffolds

2 条资料

讲义 / SlidesSlides官方课程页面新增资料；来源：https://cs329z.stanford.edu/；核对：2026-10-16。论文Yao et al. "ReAct: Synergizing Reasoning and Acting in Language Models." ICLR (2023).官方课程阅读
07

Agent Memory Architectures

5 条资料

讲义 / SlidesSlides官方课程页面新增资料；来源：https://cs329z.stanford.edu/；核对：2026-10-16。论文Packer et al. "MemGPT: Towards LLMs as Operating Systems." arXiv (2023).官方课程阅读技术文章Letta. "Agent Memory: How to Build Agents that Learn and Remember." Letta Blog (2025).官方补充阅读论文Chhikara et al. "Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory." arXiv (2025).官方补充阅读论文Park et al. "Generative Agents: Interactive Simulacra of Human Behavior." UIST (2023).官方补充阅读
08

Multi-Agent Systems

4 条资料

论文Wu et al. "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation." COLM (2024).官方课程阅读论文Cemri et al. "Why Do Multi-Agent LLM Systems Fail?" arXiv (2025).官方补充阅读技术文章Neubig. "Don't Sleep on Single-agent Systems." OpenHands Blog (2024).官方补充阅读论文Liu et al. "A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration." COLM (2024).官方补充阅读
09

Optimization

4 条资料

论文Snell et al. "Scaling LLM Test-Time Compute Optimally…" ICLR (2025).官方课程阅读论文Agrawal et al. "GEPA: Reflective Prompt Evolution Can Outperform RL." arXiv (2026).官方课程阅读论文Soylu et al. "Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together." EMNLP (2024).官方补充阅读论文Opsahl-Ong et al. "Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs." arXiv (2024).官方补充阅读
11

What Data Do Agents Need?

2 条资料

技术文章Shankar. "Data Flywheels for LLM Applications." (2024).官方课程阅读论文Tan et al. "Large Language Models for Data Annotation and Synthesis: A Survey." EMNLP (2024).官方补充阅读
12

Data Selection & Quality

3 条资料

论文Yang et al. "SWE-smith: Scaling Data for Software Engineering Agents." NeurIPS D&B (2025).官方课程阅读论文Shankar et al. "Who Validates the Validators? Aligning LLM-Assisted Evaluation with Human Preferences." UIST (2024).官方课程阅读论文Zhou et al. "LIMA: Less Is More for Alignment." NeurIPS (2023).官方补充阅读
13

Evaluation Fundamentals & Benchmark Design

3 条资料

论文Zhu et al. "Establishing Best Practices for Building Rigorous Agentic Benchmarks." (2025).官方课程阅读技术文章Press. "How to Build Good Language Modeling Benchmarks." (2024).官方补充阅读论文Polo et al. "tinyBenchmarks: Evaluating LLMs with Fewer Examples." ICML (2024).官方补充阅读
14

LLM-as-Judge & Evaluation Infrastructure

4 条资料

技术文章Grace et al. "Demystifying Evals for AI Agents." Anthropic (2026).官方课程阅读论文Zheng et al. "Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena." NeurIPS (2023).官方课程阅读论文Ryan et al. "AutoMetrics: Approximate Human Judgements with Automatically Generated Evaluators." ICLR (2026).官方课程阅读论文Zhu et al. "AutoLibra: Agent Metric Induction from Open-Ended Human Feedback." ICLR (2026).官方补充阅读
15

Agent Safety & Guardrails

6 条资料

论文Shao et al. "PrivacyLens: Evaluating Privacy Norm Awareness of LMs in Action." NeurIPS D&B (2024).官方课程阅读论文Zhang & Yang. "Searching for Privacy Risks in LLM Agents via Simulation." arXiv (2025).官方课程阅读论文Li. "Agentic LLMs as Powerful Deanonymizers." arXiv (2026).官方课程阅读论文Wen et al. "Contextualized Privacy Defense for LLM Agents." arXiv (2026).官方补充阅读技术文章OpenAI. "Understanding Prompt Injections: A Frontier Security Challenge." (2025).官方补充阅读技术文章Anthropic. "Anthropic's Responsible Scaling Policy." (2023).官方补充阅读
17

Coding & Software Agents

5 条资料

论文Yang et al. "SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering." NeurIPS (2024).官方课程阅读论文Wang et al. "OpenHands: An Open Platform for AI Software Developers." ICLR (2025).官方课程阅读技术文章Anthropic. "Claude Code: Best Practices for Agentic Coding." (2025).官方补充阅读技术文章Young. "Effective Harnesses for Long-Running Agents." Anthropic (2025).官方补充阅读论文Jimenez et al. "SWE-bench: Can Language Models Resolve Real-World GitHub Issues?" ICLR (2024).官方补充阅读
18

Proactive Agents

3 条资料

论文Shaikh et al. "Creating General User Models from Computer Use." UIST (2025).官方课程阅读论文Shaikh et al. "Learning Next Action Predictors from Human-Computer Interaction." arXiv (2026).官方补充阅读代码Steinberger. "OpenClaw: Open-source proactive AI agent." (2025).官方补充阅读
19

Frontiers & Open Problems

2 条资料

论文Xie et al. "OSWorld: Benchmarking Multimodal Agents in Real Computer Environments." NeurIPS D&B (2024).官方补充阅读论文Yao et al. "WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents." NeurIPS (2022).官方补充阅读

资料来源归原作者与课程方所有 · 笔记内容持续校订

llm_learn