The Agentic Perspective on Context Generation
A unifying, high-level interpretation of both tool use and Retrieval-Augmented Generation (RAG) is to view them as operations managed by an 'agent.' This agent is responsible for determining which external functions to call, when to call them, and how to use their outputs to generate the necessary context for the final prediction.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Consider two language model systems. System A is provided with a set of relevant documents from a database at the same time it receives a user's query, before it begins generating a response. System B, in the middle of generating a response, pauses to execute a function that fetches real-time data, then uses that data to complete its answer. From a modeling perspective, what is the most accurate description of the fundamental goal shared by both systems?
Architectural Solutions for Context-Aware AI
The fact that Retrieval-Augmented Generation (RAG) gathers information before inference begins, while tool use accesses functions during inference, means that from a modeling perspective, they serve fundamentally different purposes in enhancing language model outputs.
The Agentic Perspective on Context Generation
Learn After
Agentic Decision-Making for Complex Queries
Analyzing the Agent's Role in Context Generation
A user asks a language model system, 'What is the current stock price of Company X multiplied by the number of employees they had in 2022?' To answer, the system first calls a stock price API for the current price, then queries an internal database for the 2022 employee count, and finally performs the multiplication. From the agentic perspective, what is the primary role demonstrated by the system in this process?