让大模型自动生成复杂检索程序，精准组合文本图像与结构化数据查询。
ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis
- 用可执行的混合语言生成检索程序，融合SQL逻辑与向量检索。
- 在电商和邮件数据上超越GPT-5.5和Claude Opus，Hit@1达0.91。
- 适合需要灵活组合多源信息的智能检索系统开发者。
真实世界的检索常需在文本和图像上，通过任意布尔逻辑组合结构化约束与语义意图。现有混合管道如倒数排名融合或自查询检索器仅支持固定组合方式，而近期强化学习检索器将语言模型作为单一后端的查询生成器，无法处理异构检索路径的调度。本文提出ProRetrieval，将语言模型重构为检索编排者：给定自然语言查询，它生成一个可在混合领域特定语言（DSL）中执行的程序，该程序在结构化字段上交织使用SQL操作符与文本和图像的向量检索原语，而SQL本身提供融合异构候选集的逻辑代数。使用Qwen3-4B模型，在四层奖励机制下采用GRPO和DAPO进行训练，并在基于Amazon商品和Enron邮件构建的两个新基准上评估。4B模型在电商任务上达到Hit@1 0.81，超过GPT-5.5（0.69）；在邮件任务上达到0.91，优于Claude Opus 4.7及多种检索、大模型增强、结构化查询与图基基线。代码与数据已公开。
原文摘要 · Abstract (English)
Real-world retrieval often composes structured constraints with semantic intents over text and images through arbitrary Boolean logic. Existing hybrid pipelines such as reciprocal rank fusion or self-querying retrievers admit only a fixed form of composition, while recent reinforcement-learning retrievers train the language model as a query generator for a single backend, leaving the orchestration of heterogeneous retrieval paths outside its action space. We propose ProRetrieval, which recasts the language model as a retrieval orchestrator: given a natural-language query, it synthesizes an executable program in a hybrid DSL interleaving SQL operators over structured fields with vector-retrieval primitives over text and images, with SQL itself providing the logical algebra that fuses heterogeneous candidate sets. We train Qwen3-4B with GRPO and DAPO under a hierarchical four-term reward, and evaluate on two new benchmarks built from Amazon products and Enron email. Our 4B model surpasses GPT-5.5 (Hit@1 0.81 vs. 0.69 on e-commerce; 0.91 vs. 0.86 on email) and Claude Opus 4.7 and a comprehensive suite of retrieval, LLM-augmented, structured-query, and graph-based baselines. Code: https://anonymous.4open.science/r/ProRetrieval/; data: https://huggingface.co/datasets/anonymous-7219/ProRetrieval.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。