| 1 |
Sep 29 |
Course Introduction |
• Section 1 of How far are we from AGI?
• How to Write a Paper
• Language Agents: Foundations, Prospects, and Risks
• How to Give a Bad Talk |
| 2 |
Oct 6 |
Overview of LLM Agents
[AI Agent Overview I] |
• Section 2-3 of How far are we from AGI? |
| 3 |
Oct 13 |
Overview of LLM Agents
[AI Agent Overview II] |
• Section 4-5 of How far are we from AGI? |
| 4 |
Oct 20 |
Overview of LLM Agents
[AI Agent Overview III] |
• Section 6-7 of How far are we from AGI? |
| 5 |
Oct 27 |
Agent Ability: [Reasoning] |
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• ReAct: Synergizing Reasoning and Acting in Language Models |
| 6 |
Nov 3 |
Agent Ability: [Memory] |
• HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
• Cognitive Architectures for Language Agents |
| 7 |
Nov 10 |
Agent Ability: [Planning] |
• LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
• Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models |
| 8 |
Nov 17 |
Agent Ability: [Multi-modal Understanding] |
• Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visually Grounded Web Tasks |
| 9 |
Jan 5 |
Agent Evaluation: [via benchmarks/LLMs/VLMs] |
• Autonomous Evaluation and Refinement of Digital Agents
• Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference |
| 10 |
Jan 12 |
Agent Framework: [Tool Use] |
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• Gorilla: Large Language Model Connected with Massive APIs |
| 11 |
Jan 19 |
Agent Framework: [Retrieval-Augmented Generation] |
• Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity
• Corrective Retrieval-Augmented Generation |
| 12 |
Jan 19 |
Agent Application: [Auto-research] |
• ResearchTown: Simulator of Human Research Community
• Can Large Language Models Provide Useful Feedback on Research Papers? A Large-scale Empirical Analysis |
| 13 |
Jan 26 |
Agent Framework: [Multi-agent Systems] |
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
• CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society |
| 14 |
Jan 26 |
Agent Application: [Coding Agents] |
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents |
| 15 |
Feb 2 |
Agent Application: [Social Agents] |
• Generative Agents: Interactive Simulacra of Human Behavior
• SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents |
