Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search

• URL: http://arxiv.org/abs/2606.15911v1
• Date: Sun, 14 Jun 2026 16:40:41 GMT
• Title: Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search
• Abstract summary: This paper focuses on automatically generating informative ad descriptions in sponsored search.<n>We propose Interactor, a multi-turn iterative creation framework optimized with agentic RL for ad description generation.
• Score: 12.65264204975306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper focuses on automatically generating informative ad descriptions in sponsored search. Unlike ad titles which are usually optimized to attract user click feedbacks, ad descriptions have a longer text span and possess the potential of incorporating world knowledge to address user search intents while presenting the fine-grained selling points of the ads. We propose Interactor, a multi-turn iterative creation framework optimized with agentic RL for ad description generation. The generation model acts as a policy that interacts with a customized environment consisting of multiple generative reward models. Given initial generations by the policy, the customized GenRMs evaluate multi-dimensional qualities including knowledge capacity and landing page consistency, providing both binary signals and reasoning feedbacks. The policy then iteratively refines the descriptions based on such feedbacks to ensure continuous improvement. Experiments on industrial datasets show that the Interactor framework significantly outperforms state-of-the-art approaches in generating knowledge-rich and faithful ad descriptions. Since May 2026, it has been deployed online in a leading search ads system, contributing to both ad revenue and user experience.

Related papers

• AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and Tool Coevolution [10.959681786863412]
  We propose AdsWorldEngine, an agentic framework for conversational advertising.<n>AdsWorldEngine uses an Opportunity Gate to determine whether ads should be shown, an Orchestrator to generate commercial intents, call advertising tools, and construct a top-3 ad slate.<n>Offline, AdsWorldEngine improves diversity by 60% and relevance by 80% over the current production ad delivery system.
  arXiv  Detail & Related papers  (2026-08-13T23:53:05Z)
• Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models [75.31791398000492]
  We develop a Unified Advertisement Generative model (Uni-AdGen) that employs a single autoregressive framework to produce both advertising images and texts.<n>To further personalize advertisements, we equip Uni-AdGen with a coarse-to-fine preference understanding module.<n>Our method outperforms baselines in general and personalized advertisement generation.
  arXiv  Detail & Related papers  (2026-05-12T13:58:06Z)
• Detecting RAG Advertisements Across Advertising Styles [24.080227437136585]
  We develop a taxonomy of advertising styles for large language models (LLMs)<n>We simulate that advertisers may attempt to evade detection by changing their advertising style.<n>We evaluate a variety of ad-detection approaches with respect to their robustness.
  arXiv  Detail & Related papers  (2026-03-05T08:16:21Z)
• NextAds: Towards Next-generation Personalized Video Advertising [46.666292153282875]
  NextAds is a generation-based paradigm for next-generation personalized video advertising.<n>We formulate two representative tasks: personalized creative generation and personalized creative integration.<n>We conduct initial exploratory experiments, demonstrating that GenAI can generate and integrate personalized creatives with encouraging performance.
  arXiv  Detail & Related papers  (2026-03-02T17:58:07Z)
• Open Multimodal Retrieval-Augmented Factual Image Generation [86.34546873830152]
  We introduce ORIG, an agentic open multimodal retrieval-augmented framework for Factual Image Generation (FIG)<n> ORIG iteratively retrieves and filters multimodal evidence from the web and incrementally integrates the refined knowledge into enriched prompts to guide generation.<n>Experiments demonstrate that ORIG substantially improves factual consistency and overall image quality over strong baselines.
  arXiv  Detail & Related papers  (2025-10-26T04:13:31Z)
• SUMMA: A Multimodal Large Language Model for Advertisement Summarization [15.514886325064792]
  We propose SUMMA, a model that processes video ads into summaries highlighting the content of highest commercial value.<n> SUMMA is developed via a two-stage training strategy-multimodal supervised fine-tuning followed by reinforcement learning.<n>Online experiments show a statistically significant 1.5% increase in advertising revenue.
  arXiv  Detail & Related papers  (2025-08-28T09:19:53Z)
• TeamCMU at Touché: Adversarial Co-Evolution for Advertisement Integration and Detection in Conversational Search [1.187456026346823]
  integration of advertisements into generated responses presents both commercial opportunities and challenges for user experience.<n>We propose a modular pipeline for advertisement management in RAG-based conversational systems, consisting of an ad-rewriter for seamless ad integration and a robust ad-classifier for detection.
  arXiv  Detail & Related papers  (2025-07-01T07:24:29Z)
• LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification [78.73711446918814]
  We propose a novel framework named LATex for AG-ReID, which adopts prompt-tuning strategies to leverage attribute-based text knowledge.<n>Our framework can fully leverage attribute-based text knowledge to improve AGReID performance.
  arXiv  Detail & Related papers  (2025-03-31T04:47:05Z)
• CTR-Driven Advertising Image Generation with Multimodal Large Language Models [53.40005544344148]
  We explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective.<n>To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL)<n>Our method achieves state-of-the-art performance in both online and offline metrics.
  arXiv  Detail & Related papers  (2025-02-05T09:06:02Z)
• DistinctAD: Distinctive Audio Description Generation in Contexts [62.58375366359421]
  We propose DistinctAD, a framework for generating Audio Descriptions that emphasize distinctiveness to produce better narratives.<n>To address the domain gap, we introduce a CLIP-AD adaptation strategy that does not require additional AD corpora.<n>In Stage-II, DistinctAD incorporates two key innovations: (i) a Contextual Expectation-Maximization Attention (EMA) module that reduces redundancy by extracting common bases from consecutive video clips, and (ii) an explicit distinctive word prediction loss that filters out repeated words in the context.
  arXiv  Detail & Related papers  (2024-11-27T09:54:59Z)
• A Multimodal Framework for Video Ads Understanding [64.70769354696019]
  We develop a multimodal system to improve the ability of structured analysis of advertising video content. Our solution achieved a score of 0.2470 measured in consideration of localization and prediction accuracy, ranking fourth in the 2021 TAAC final leaderboard.
  arXiv  Detail & Related papers  (2021-08-29T16:06:00Z)
• Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement [26.70647666598025]
  We study approaches to refine the given ad text and image by: (i) generating new ad text, (ii) recommending keyphrases for new ad text, and (iii) recommending image tags (objects in image) Based on A/B tests conducted by multiple advertisers, we form pairwise examples of inferior and superior ad creatives. We also share broadly applicable insights from our experiments using data from the Yahoo Gemini ad platform.
  arXiv  Detail & Related papers  (2020-08-17T16:46:28Z)
• Recommending Themes for Ad Creative Design via Visual-Linguistic Representations [27.13752835161338]
  We propose a theme (keyphrase) recommender system for ad creative strategists. The theme recommender is based on aggregating results from a visual question answering (VQA) task. We show that cross-modal representations lead to significantly better classification accuracy and ranking precision-recall metrics.
  arXiv  Detail & Related papers  (2020-01-20T18:04:10Z)

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.