OMS: On-the-fly, Multi-Objective, Self-Reflective Ad Keyword Generation via LLM Agent

TL;DR

OMS is a novel framework for real-time, multi-objective, self-evaluating keyword generation in sponsored search advertising, overcoming data reliance and enabling adaptive, performance-driven keyword optimization.

Contribution

It introduces a training-free, online adaptive keyword generation method that employs multi-objective reasoning and self-reflection for improved ad campaign performance.

Findings

Outperforms existing keyword generation methods on benchmarks and real campaigns.

Each component's effectiveness is validated through ablation and human evaluations.

Demonstrates improved online performance monitoring and multi-metric optimization.

Abstract

Keyword decision in Sponsored Search Advertising is critical to the success of ad campaigns. While LLM-based methods offer automated keyword generation, they face three major limitations: reliance on large-scale query-keyword pair data, lack of online multi-objective performance monitoring and optimization, and weak quality control in keyword selection. These issues hinder the agentic use of LLMs in fully automating keyword decisions by monitoring and reasoning over key performance indicators such as impressions, clicks, conversions, and CTA effectiveness. To overcome these challenges, we propose OMS, a keyword generation framework that is On-the-fly (requires no training data, monitors online performance, and adapts accordingly), Multi-objective (employs agentic reasoning to optimize keywords based on multiple performance metrics), and Self-reflective (agentically evaluates keyword quality). Experiments on benchmarks and real-world ad campaigns show that OMS outperforms existing methods; ablation and human evaluations confirm the effectiveness of each component and the quality of generated keywords.