CMU LLM Inference (10): Incorporating Tools

This lecture (by Graham Neubig) for CMU CS 11-763, Advanced NLP (Fall 2025) covers: What are tools? Definition and taxonomy Basic tool use paradigm Key approaches: PAL, Toolformer, Gorilla, WebGPT Tool creation: TroVE and Large Language Models as Tool Makers Tool robustness: Benchmarking failures in tool-augmented language models Standardized function calling (JSON Schema) Parallel function calling Model Context Protocol (MCP) and MCP registries FastMCP framework for rapid MCP development Sandboxed code execution for secure tool use Tool use scenarios and trade-offs Evaluation challenges and best practices Class Site: https://phontron.com/class/lminferenc...

Join Today
CMU LLM Inference (11): Agents and Multi-Agent Communication
▶︎

CMU LLM Inference (11): Agents and Multi-Agent Communication

Lecture 58: Disaggregated LLM Inference
▶︎

Lecture 58: Disaggregated LLM Inference

[CVPR 2026] 1st Workshop on Generative 3D Reconstruction - Christian Rupprecht
▶︎

[CVPR 2026] 1st Workshop on Generative 3D Reconstruction - Christian Rupprecht

CMU LLM Inference (1): Introduction to Language Models and Inference
▶︎

CMU LLM Inference (1): Introduction to Language Models and Inference

CMU Advanced NLP Fall 2024 (7): Prompting and Complex Reasoning
▶︎

CMU Advanced NLP Fall 2024 (7): Prompting and Complex Reasoning

Generative AI and the Online Information Ecosystem: Early Evidence and Implications (Ananya Sen)
▶︎

Generative AI and the Online Information Ecosystem: Early Evidence and Implications (Ananya Sen)

Yann LeCun's $1B Bet Against LLMs [Part 1]
▶︎

Yann LeCun's $1B Bet Against LLMs [Part 1]

CMU LLM Inference (7): Chain of Thought and Intermediate Steps
▶︎

CMU LLM Inference (7): Chain of Thought and Intermediate Steps

CMU LLM Inference (9): Reasoning Models
▶︎

CMU LLM Inference (9): Reasoning Models

CMU Advanced NLP Fall 2024 (6): Instruction Tuning
▶︎

CMU Advanced NLP Fall 2024 (6): Instruction Tuning

CMU LLM Inference (2): Probability Review and Code Examples
▶︎

CMU LLM Inference (2): Probability Review and Code Examples

RI Seminar: Max Simchowitz: Generative Control, Action Chunking, and Moravec’s Paradox
▶︎

RI Seminar: Max Simchowitz: Generative Control, Action Chunking, and Moravec’s Paradox

CMU LLM Inference (4): Beam Search and Variants
▶︎

CMU LLM Inference (4): Beam Search and Variants

CMU Advanced NLP Fall 2024 (14): Ensembling and Mixture of Experts
▶︎

CMU Advanced NLP Fall 2024 (14): Ensembling and Mixture of Experts

CMU LLM Inference (12): Reward Models and Best-of-N
▶︎

CMU LLM Inference (12): Reward Models and Best-of-N

CMU LLM Inference (8): Self-Refine and Self-Correction Methods
▶︎

CMU LLM Inference (8): Self-Refine and Self-Correction Methods

Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker
▶︎

Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

Don't learn AI Agents without Learning these Fundamentals
▶︎

Don't learn AI Agents without Learning these Fundamentals

CMU Advanced NLP Fall 2024 (17): Evaluation and Multimodal
▶︎

CMU Advanced NLP Fall 2024 (17): Evaluation and Multimodal

CMU Advanced NLP Fall 2024 (10): Retrieval and RAG
▶︎

CMU Advanced NLP Fall 2024 (10): Retrieval and RAG