Optimizing AI Agent Selection: A Performance and Cost Analysis Using a Single PDF Dataset

In this paper, we explore how different AI agents perform when handling PDF queries—both simple and complex. We compare their execution speed, memory use, token consumption, and cost, focusing on the OpenAI Agent, ReAct Agent, LLM Compiler Agent, and LLM Chain-of-Abstraction Agent.

In this paper, we explore how different AI agents perform when handling PDF queries—both simple and complex. We compare their execution speed, memory use, token consumption, and cost, focusing on the OpenAI Agent, ReAct Agent, LLM Compiler Agent, and LLM Chain-of-Abstraction Agent.