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

• URL: http://arxiv.org/abs/2601.05257v1
• Date: Mon, 20 Oct 2025 16:13:48 GMT
• Title: KP-Agent: Keyword Pruning in Sponsored Search Advertising via LLM-Powered Contextual Bandits
• Abstract summary: We propose KP-Agent, an agentic system with domain tool set and a memory module.<n>By modeling keyword pruning within a contextual bandit framework, KP-Agent generates code snippets to refine keyword sets.<n> Experiments show KP-Agent improves cumulative profit by up to 49.28% over baselines.
• Score: 6.509467428557859
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• GrepSeek: Training Search Agents for Direct Corpus Interaction [66.69568141699311]
  GrepSeek is an optimized direct corpus interaction (DCI) search agent that trains a compact search agent to find, filter, and compose evidence from large text corpora.<n>To make DCI practical at scale, we further use a semantics-preserving sharded-parallel execution engine that accelerates shell-based retrieval by up to $7.6times$ while preserving byte-exact equivalence with sequential execution of the shell command.
  arXiv  Detail & Related papers  (2026-05-28T03:37:33Z)
• SAGE: Benchmarking and Improving Retrieval for Deep Research Agents [60.53966065867568]
  We introduce SAGE, a benchmark for scientific literature retrieval comprising 1,200 queries across four scientific domains, with a 200,000 paper retrieval corpus.<n>We evaluate six deep research agents and find that all systems struggle with reasoning-intensive retrieval.<n> BM25 significantly outperforms LLM-based retrievers by approximately 30%, as existing agents generate keyword-oriented sub-queries.
  arXiv  Detail & Related papers  (2026-02-05T18:25:24Z)
• AgenticTagger: Structured Item Representation for Recommendation with LLM Agents [58.12004213978182]
  AgenticTagger is a framework that queries LLMs for representing items with sequences of text descriptors.<n>To effectively and efficiently ground vocabulary in the item corpus of interest, we design a multi-agent reflection mechanism.<n>Experiments on public and private data show AgenticTagger brings consistent improvements across diverse recommendation scenarios.
  arXiv  Detail & Related papers  (2026-02-05T18:01:37Z)
• LLMs as Sparse Retrievers:A Framework for First-Stage Product Search [103.70006474544364]
  Product search is a crucial component of modern e-commerce platforms, with billions of user queries every day.<n>Sparse retrieval methods suffer from severe vocabulary mismatch issues, leading to suboptimal performance in product search scenarios.<n>With their potential for semantic analysis, large language models (LLMs) offer a promising avenue for mitigating vocabulary mismatch issues.<n>We propose PROSPER, a framework for PROduct search leveraging LLMs as SParsE Retrievers.
  arXiv  Detail & Related papers  (2025-10-21T11:13:21Z)
• FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents [76.12500510390439]
  Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals.<n>Existing pruning strategies either discard relevant content or retain irrelevant context, leading to suboptimal action prediction.<n>We introduce FocusAgent, a simple yet effective approach that leverages a lightweight LLM retriever to extract the most relevant lines from accessibility tree (AxTree) observations.
  arXiv  Detail & Related papers  (2025-10-03T17:41:30Z)
• OMS: On-the-fly, Multi-Objective, Self-Reflective Ad Keyword Generation via LLM Agent [5.73568333009566]
  Keywords decision is critical to the success of Sponsored Search Advertising campaigns.<n>OMS is a framework for keyword generation that is On-the-fly (requires no training data, monitors online performance, and adapts accordingly)<n>Experiments on benchmarks and real-world ad campaigns show that OMS outperforms existing methods.
  arXiv  Detail & Related papers  (2025-07-03T06:37:55Z)
• Real-time Ad retrieval via LLM-generative Commercial Intention for Sponsored Search Advertising [4.16793449447122]
  We propose the Real-time Ad REtrieval (RARE) framework to retrieve ads for queries in real-time.<n>RARE uses commercial intentions (CIs) as an intermediate semantic representation to directly retrieve ads for queries in real-time.<n>Online implementation has yielded significant benefits: a 5.04% increase in consumption, a 6.37% rise in Gross Merchandise Volume (GMV), a 1.28% enhancement in click-through rate (CTR) and a 5.29% increase in shallow conversions.
  arXiv  Detail & Related papers  (2025-04-02T02:26:31Z)
• Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models [52.829293635314194]
  Keyphrase generation is a long-standing NLP task for automatically generating keyphrases for a given document.<n>We focus on the zero-shot capabilities of open-source instruction-tuned LLMs (Phi-3, Llama-3) and the closed-source GPT-4o for this task.
  arXiv  Detail & Related papers  (2025-03-01T19:38:57Z)
• OKG: On-the-Fly Keyword Generation in Sponsored Search Advertising [11.100360578510223]
  On-the-fly Keyword Generation (OKG) is an agent-based method that monitors changes and adapts keyword generation in real time.<n>OKG significantly improves adaptability and responsiveness compared to traditional methods.
  arXiv  Detail & Related papers  (2024-11-18T03:02:06Z)
• KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning [25.421649004269373]
  In task-oriented dialogs (TOD), reinforcement learning algorithms train a model to directly optimize response for task-related metrics. We investigate an approach to create a more efficient RL-based algorithm to improve TOD performance in an offline setting. Experiments on the MultiWoZ dataset show our new training algorithm, Keywords Reinforcement Learning with Next-word Sampling (KRLS), achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-11-30T06:27:46Z)
• Keyword Targeting Optimization in Sponsored Search Advertising: Combining Selection and Matching [0.0]
  An optimal keyword targeting strategy guarantees reaching the right population effectively. This paper aims to address the keyword targeting problem, which is a challenging task because of the incomplete information of historical advertising performance indices. Experimental results show that, (a) BB-KSM outperforms seven baselines in terms of profit; (b) BB-KSM shows its superiority as the budget increases.
  arXiv  Detail & Related papers  (2022-10-19T03:37:32Z)
• Keyword Optimization in Sponsored Search Advertising: A Multi-Level Computational Framework [20.22050119811848]
  Keywords serve as an essential bridge linking advertisers, search users and search engines. This paper proposes a multi-level and closed-form computational framework for keyword optimization.
  arXiv  Detail & Related papers  (2022-02-28T02:03:14Z)
• Deep Keyphrase Completion [59.0413813332449]
  Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval. We propose textitkeyphrase completion (KPC) to generate more keyphrases for document (e.g. scientific publication) taking advantage of document content along with a very limited number of known keyphrases. We name it textitdeep keyphrase completion (DKPC) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework
  arXiv  Detail & Related papers  (2021-10-29T07:15:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.