发表机构
Airbnb, Inc.（爱彼迎公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SCOUT提出供给感知的主动查询建议框架，利用供给侧反馈和GRPO优化，解决旅行搜索冷启动问题，提升库存匹配率12.3%并保持多样性。
AI 中文摘要
由大型语言模型（LLMs）驱动的生成式查询建议在搜索和对话系统中日益流行，以减少用户摩擦并引导意图形成。现有方法将建议与用户偏好（如点击或转化）对齐。这适用于开放式应用，如聊天机器人和个人助理，在这些场景中结果空间不受约束或历史用户自由文本查询丰富。然而，将这些方法应用于旅行搜索存在两个局限性。首先，旅行搜索从根本上受物理库存约束；一个查询（例如“浪漫的海滨别墅”）在巴厘岛可能产生丰富的结果，但在东京却很少，因此仅与用户偏好对齐并不能基于可提供的供给。其次，旅行平台传统上依赖分面搜索界面，没有自由文本查询。这造成了冷启动问题：没有历史查询日志，就没有需求侧数据用于对齐；在请求时没有种子查询，建议必须仅从结构化上下文主动生成。为解决这些挑战，我们提出SCOUT，一个用于供给感知主动查询建议的引导框架。SCOUT通过用供给侧系统反馈替代缺失的需求侧用户反馈来克服数据缺口。它将搜索引擎视为强化学习环境，从生产重排序器的查询-列表匹配分数中推导出密集奖励，并使用组相对策略优化（GRPO）优化策略。SCOUT将库存匹配率（IMR@18）提高12.3%，同时保持多样性，以零边际推理成本匹配计算密集型的best-of-8策略，使供给感知建议可在实时旅行搜索路径上部署。
英文摘要
Generative query suggestion, powered by Large Language Models (LLMs), has become increasingly popular in search and conversational systems to reduce user friction and guide intent formulation. Existing approaches align suggestions with user preferences (e.g., clicks or conversions). This works for open-ended applications like chatbots and personal assistants, where the result space is unconstrained or historical user free-text queries are abundant. However, applying these methods to travel search presents two limitations. First, travel search is fundamentally constrained by physical inventory; a query (e.g., "romantic beachfront villa") may yield abundant results in Bali but few in Tokyo, so aligning with user preferences is not by itself grounded in what can be offered. Second, travel platforms traditionally rely on faceted search interfaces with no free-text queries. This creates a cold-start problem: without historical query logs there is no demand-side data for alignment, and without a seed query at request time, suggestions must be generated proactively from structured context alone. To address these challenges, we propose SCOUT, a bootstrapping framework for supply-aware proactive query suggestion. SCOUT overcomes the data gap by substituting missing demand-side user feedback with supply-side system feedback. It treats the search engine as a reinforcement learning environment, deriving a dense reward from the production reranker's query-listing match scores, and optimizes the policy with Group Relative Policy Optimization (GRPO). SCOUT improves inventory match rate (IMR@18) by 12.3% while preserving diversity, matching a compute-intensive best-of-8 policy at zero marginal inference cost and making supply-aware suggestion deployable on a real-time travel search path.
CommentsAccepted at the CIKM 2026 Workshop on Generative, Retrieval-augmented, and Agentic Intelligence for Personalization
