Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations
作者: Zhuohang Jiang, Yuxin Chen, Shijie Wang, Haohao Qu, Zhou Jindong, Wenqi Fan, Li Qing, Dongxu Liang, Jun Wang
分类: cs.IR, cs.AI
发布日期: 2026-06-09
期刊: Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '26), August 09--13, 2026, Jeju Island, Republic of Korea
💡 一句话要点
提出AIR框架以解决跨域推荐中的语义差距问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 跨域推荐 用户意图 大型语言模型 推理加速 电商应用 语义理解 在线推荐
📋 核心要点
- 跨域推荐面临语义差距和用户行为序列噪声等多重挑战,现有方法难以有效应对。
- 本文提出AIR框架,通过将LLM推理迁移到离线阶段,动态构建用户意图表示,从而提升推荐效果。
- 实验结果显示,该方法在公共数据集上实现了最先进的性能,并在实际业务中显著提升了核心指标。
📝 摘要(中文)
跨域推荐是内容到电商平台的核心问题,旨在利用用户与内容的交互推断电商侧的潜在购买意图。然而,现有方法面临语义差距和用户行为序列噪声等挑战。本文提出AIR(Atomic Intent Reasoning)框架,通过将LLM推理迁移到离线阶段,并在在线操作中动态构建用户意图表示,实现了约400倍的推理加速,同时保持语义一致性。实验结果表明,该方法在多个公共数据集上达到了最先进的性能,并在Kuaishou电商的实际业务场景中进行了大规模在线A/B测试,显示出核心业务指标的显著提升,验证了其在工业级推荐系统中的有效性和实际价值。
🔬 方法详解
问题定义:本文旨在解决跨域推荐中的语义差距和用户行为序列噪声问题。现有方法在处理大规模用户行为数据时,推理延迟较高,难以满足在线推荐的实时性要求。
核心思路:AIR框架的核心思路是将大型语言模型(LLM)的推理过程迁移到离线阶段,并在在线操作中通过高效的检索和组合动态构建用户意图表示,从而实现快速推理和语义一致性。
技术框架:该框架主要包括离线推理模块和在线意图构建模块。离线模块负责处理用户行为数据并生成意图表示,而在线模块则根据实时用户交互动态调整推荐结果。
关键创新:AIR框架的最大创新在于将LLM推理与用户意图表示的动态构建相结合,显著降低了推理延迟,同时保持了推荐的语义准确性。这一设计与传统的在线推理方法形成了鲜明对比。
关键设计:在技术细节上,AIR框架采用了高效的检索算法和意图组合策略,以确保在大规模数据下仍能快速响应用户请求。具体的损失函数和网络结构设计也经过优化,以提升模型的学习效果和推理速度。
🖼️ 关键图片
📊 实验亮点
在多个公共数据集上,AIR框架实现了最先进的性能,推理速度提升约400倍。此外,在Kuaishou电商的实际业务场景中,核心业务指标如GMV提升了3.446%,验证了其在工业级推荐系统中的有效性。
🎯 应用场景
AIR框架在电商推荐系统中具有广泛的应用潜力,能够有效提升用户的购买转化率和商业价值。其设计理念也可扩展到其他领域,如社交媒体推荐和内容分发系统,未来可能对推荐系统的实时性和准确性产生深远影响。
📄 摘要(原文)
Cross-domain recommendation is a core problem in content-to-e-commerce platforms. Its objective is to leverage user interactions with content to infer potential purchasing intent on the e-commerce side, thereby enhancing conversion rates and commercial value. However, in real industrial scenarios, cross-domain recommendation faces multiple challenges: significant semantic gaps exist between different domains, and user cross-domain behavior sequences are often massive in scale and rich in noise. Although large language models (LLMs) possess powerful semantic understanding and reasoning capabilities, their millisecond-level inference latency makes direct application in online recommendation systems difficult. To address these issues, this paper introduces AIR (Atomic Intent Reasoning), an LLM-driven cross-domain recommendation framework designed for industrial-grade deployment. By migrating LLM inference to the offline phase and dynamically constructing user intent representations through efficient retrieval and composition during online operations, it achieves approximately 400* inference acceleration while maintaining semantic consistency. Experimental results across multiple public datasets demonstrate that our method achieves state-of-the-art performance in cross-domain recommendation tasks. Furthermore, large-scale online A/B testing conducted in Kuaishou E-commerce's real-world business scenarios shows that our approach delivers stable and significant improvements across multiple core business metrics, including a +3.446% increase in GMV, fully validating its effectiveness and practical value in industrial-scale recommendation systems.