KP-Agent: Keyword Pruning in Sponsored Search Advertising via LLM-Powered Contextual Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Long, Hou-Wan, Song, Yicheng, Wang, Zidong, Sun, Tianshu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911362061434880
author Long, Hou-Wan
Song, Yicheng
Wang, Zidong
Sun, Tianshu
author_facet Long, Hou-Wan
Song, Yicheng
Wang, Zidong
Sun, Tianshu
contents Sponsored search advertising (SSA) requires advertisers to constantly adjust keyword strategies. While bid adjustment and keyword generation are well-studied, keyword pruning-refining keyword sets to enhance campaign performance-remains under-explored. This paper addresses critical inefficiencies in current practices as evidenced by a dataset containing 0.5 million SSA records from a pharmaceutical advertiser on search engine Meituan, China's largest delivery platform. We propose KP-Agent, an LLM agentic system with domain tool set and a memory module. By modeling keyword pruning within a contextual bandit framework, KP-Agent generates code snippets to refine keyword sets through reinforcement learning. Experiments show KP-Agent improves cumulative profit by up to 49.28% over baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05257
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KP-Agent: Keyword Pruning in Sponsored Search Advertising via LLM-Powered Contextual Bandits
Long, Hou-Wan
Song, Yicheng
Wang, Zidong
Sun, Tianshu
Information Retrieval
Artificial Intelligence
Sponsored search advertising (SSA) requires advertisers to constantly adjust keyword strategies. While bid adjustment and keyword generation are well-studied, keyword pruning-refining keyword sets to enhance campaign performance-remains under-explored. This paper addresses critical inefficiencies in current practices as evidenced by a dataset containing 0.5 million SSA records from a pharmaceutical advertiser on search engine Meituan, China's largest delivery platform. We propose KP-Agent, an LLM agentic system with domain tool set and a memory module. By modeling keyword pruning within a contextual bandit framework, KP-Agent generates code snippets to refine keyword sets through reinforcement learning. Experiments show KP-Agent improves cumulative profit by up to 49.28% over baselines.
title KP-Agent: Keyword Pruning in Sponsored Search Advertising via LLM-Powered Contextual Bandits
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2601.05257