RTBAgent: A LLM-based Agent System for Real-Time Bidding

TL;DR

RTBAgent introduces a novel LLM-based system for real-time bidding that improves decision-making accuracy and profitability by integrating reasoning, auxiliary modules, and historical data review in dynamic online advertising environments.

Contribution

This paper presents the first LLM-based RTB agent system, combining real-time environment synchronization, auxiliary modules, and a two-step decision process for adaptive bidding.

Findings

Significantly improves profitability in real advertising datasets.

Enhances decision-making adaptability to market fluctuations.

Demonstrates the effectiveness of LLMs in real-time bidding scenarios.

Abstract

Real-Time Bidding (RTB) enables advertisers to place competitive bids on impression opportunities instantaneously, striving for cost-effectiveness in a highly competitive landscape. Although RTB has widely benefited from the utilization of technologies such as deep learning and reinforcement learning, the reliability of related methods often encounters challenges due to the discrepancies between online and offline environments and the rapid fluctuations of online bidding. To handle these challenges, RTBAgent is proposed as the first RTB agent system based on large language models (LLMs), which synchronizes real competitive advertising bidding environments and obtains bidding prices through an integrated decision-making process. Specifically, obtaining reasoning ability through LLMs, RTBAgent is further tailored to be more professional for RTB via involved auxiliary modules, i.e., click-through rate estimation model, expert strategy knowledge, and daily reflection. In addition, we propose a two-step decision-making process and multi-memory retrieval mechanism, which enables RTBAgent to review historical decisions and transaction records and subsequently make decisions more adaptive to market changes in real-time bidding. Empirical testing with real advertising datasets demonstrates that RTBAgent significantly enhances profitability. The RTBAgent code will be publicly accessible at: https://github.com/CaiLeng/RTBAgent.