English(EN) ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis

ProRetrieval系统合成混合搜索程序，性能超越GPT-5.5和Claude Opus 4.7

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-27 12:03

研究人员开发了ProRetrieval，一个新颖的系统，通过合成可执行程序来编排混合搜索查询。该系统将结构化查询运算符与向量检索原语相结合，实现了文本和图像搜索的复杂逻辑组合。ProRetrieval使用Qwen3-4B配合GRPO和DAPO进行训练，并在源自亚马逊产品和Enron邮件的新基准测试中表现出色，性能超越了GPT-5.5和Claude Opus 4.7等模型。 AI

影响这项研究推进了混合搜索能力，有望改善LLM在复杂查询中与结构化和非结构化数据的交互方式。

排序理由该集群包含一篇详细介绍信息检索新系统和基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

ProRetrieval系统合成混合搜索程序，性能超越GPT-5.5和Claude Opus 4.7

本文如何被排名

Signal score: 3 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍信息检索新系统和基准的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Nan Du · 2026-08-27 12:03

ProRetrieval：通过可执行程序合成学习编排混合搜索

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 reinfor…

本文如何被排名

报道来源 [1]

ProRetrieval：通过可执行程序合成学习编排混合搜索

相关实体

相关话题