How AI Agents Use Tools: Function Calling & MCP | Stanford CS329Z Lecture 4 with Diyi Yang

How AI Agents Use Tools: Function Calling & MCP | Stanford CS329Z Lecture 4 with Diyi Yang

Title history
  • How AI Agents Use Tools: Function Calling & MCP | Stanford CS329Z Lecture 4 with Diyi Yang — observed on 20261112-2113 UTC (YouTube)
🎙 Diyi Yang 👥 1.3M 📅 November 12, 2026 ⏱ 79 min 👁 64 📄 literature review 🧭 2026-11-12
Available in: English (current) Français

Keywords

toolsfunction callingMCPRAGevaluation

Summary

This Stanford CS329Z lecture by Diyi Yang provides a comprehensive overview of how AI agents use tools, focusing on function calling and the Model Context Protocol (MCP). The lecture begins with a recap of retrieval-augmented generation (RAG) and its pitfalls, including the ’lost in the middle’ phenomenon and citation hallucination. It then explains why LLMs need external tools, covering limitations like poor arithmetic and lack of real-time data. The core of the lecture discusses methods for teaching models to use tools, such as Toolformer and ToolkenGPT, and scaling to thousands of APIs with ToolLLM and Gorilla. It also contrasts REST APIs, function calling, and MCP, and reviews evaluation benchmarks like BFCL, ToolBench, and τ-bench, along with common failure modes. The speaker integrates multiple research papers and provides practical guidance for building agentic systems.

133 words

Critical Evaluation

Value of the Information & Strength of the Argument

The lecture offers high value by systematically organizing a broad and rapidly evolving field. It clearly explains the motivations for tool use, illustrates technical approaches with concrete examples, and evaluates their effectiveness. The argumentation is strong, as it is built on established research and includes critical analysis of limitations such as hallucinated citations and position bias. The speaker also integrates audience questions to clarify concepts, reinforcing the depth of coverage.

Scientific Rigor, Source Quality, Title Accuracy

The lecture is scientifically rigorous, presenting multiple peer-reviewed methods and benchmarks from reputable sources. The instructor, Diyi Yang, is a Stanford professor with relevant expertise. Sources are numerous, including cited papers like Toolformer, Gorilla, and the lost-in-the-middle study. The title accurately matches the content, which is centered on tool use, function calling, and MCP. The description provides links to the course website and related resources, further lending credibility.

153 words

Title / Content Match

Title accurately describes the lecture content on AI agents using tools, function calling and MCP.

Quality & Reliability

8/10

Lecture from Stanford Online, presented by a professor, rigorous and well-structured, but not original research.

Key Moments

Cited Sources

Contribution & Novelties

This lecture provides a structured synthesis of current research on tool use in AI agents, bridging algorithmic methods with practical engineering standards like MCP. It highlights the progression from learning tool selection to scaling to thousands of APIs and standardizing interfaces. The discussion of evaluation benchmarks and failure modes is particularly valuable for practitioners.

Pour aller plus loin :

124 words

Radar Profile

The radar shows high scores across quantity, quality, technical level, and reliability, indicating a thorough and well-sourced academic lecture.

Reliability 8/10