ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis

2026-08-27

AI Summary

该研究提出ProRetrieval，通过合成可执行程序整合结构化和非结构化检索路径，解决现有混合检索方法的局限性。

Abstract

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.

Problem

• Hybrid Search
• Executable Program Synthesis
• Structured Constraints
• Semantic Intents
• Heterogeneous Retrieval Paths

Innovation

• executable program synthesis
• retrieval orchestrator
• hybrid DSL
• SQL operators and vector-retrieval primitives
• heterogeneous retrieval paths