ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis

[2608.27017] ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis Skip to main content Search Submit Donate Log in Computer Science > Information Retrieval arXiv:2608.27017 (cs) [Submitted on 27 Aug 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis Authors: Chengsong You , Zhen Sun , Yunhai Hu , Junwei Zhou , Xiaoyu Cao , Binyu Li , Ziyan Zhao , Weiyao Wang , Liren Lu , Zhijie Ye , Yumo Cao , Yitao Long , Yiwei Xu , Qiyi Jiang , Xuanyi Fu , Yufan Chen , Yilun Li , Rongkang Xiong , Yiran Zou , Nan Du View PDF HTML (experimental) 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: this https URL data: this https URL . Comments: 15 pages, 5 figures, 6 tables Subjects: Information Retrieval (cs.IR) ACM classes: H.3.3; I.2.7 Cite as: arXiv:2608.27017 [cs.IR] (or arXiv:2608.27017v2 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2608.27017 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chengsong You [ view email ] [v1] Thu, 27 Aug 2026 12:03:30 UTC (5,091 KB) [v2] Fri, 28 Aug 2026 07:41:47 UTC (5,091 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.IR < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis#779392
• Problem representation for refinement#90032
• VLM Fine-Tuning for End-to-End Combinatorial Optimization#1132376
• CQ4OE: A benchmark for assessing LLM-assisted ontology generation from competency questions#1061934
• The impact of using different choice functions when solving CSPs with autonomous search#935621