DSL-R1：从SQL到DSL，通过强化学习在结构化和非结构化数据上训练检索代理
DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning
AI总结：
本文提出DSL-R1框架，结合逻辑推理与语义匹配，通过强化学习优化DSL生成，提升检索性能，实现在结构化和非结构化数据上的改进。
摘要：
在复杂领域中有效检索需要弥合结构化元数据与非结构化内容之间的差距。现有系统通常将这些能力隔离，依赖于符号过滤或向量相似性，无法捕捉它们的相互作用。本文提出DSL-R1，一种统一框架，通过新颖的领域特定语言（DSL）协同逻辑推理与语义匹配。通过将向量原语嵌入SQL式运算符中，我们的方法利用符号精度和语义覆盖的互补优势。我们进一步引入强化学习机制，其中基于规则的执行反馈和检索质量奖励共同优化DSL生成，平衡结构正确性与语义对齐。在大规模工业电子邮件基准测试中，DSL-R1在Hit@1/3上实现了+12.3%的提升，一致优于解耦基线，并建立了混合检索的稳健范式。
英文摘要：
Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relying on either symbolic filtering or vector similarity, failing to capture their interplay. In this work, we propose DSL-R1, a unified framework that synergizes logical reasoning with semantic matching via a novel Domain-Specific Language (DSL). By embedding vector primitives within SQL-style operators, our approach leverages the complementary strengths of symbolic precision and semantic coverage. We further introduce a reinforcement learning mechanism where rule-based execution feedback and retrieval quality rewards jointly optimize the DSL generation, balancing structural correctness and semantic alignment. Evaluations on a large-scale industrial email benchmark demonstrate that DSL-R1 achieves a +12.3% improvement in Hit@1/3, consistently outperforming decoupled baselines and establishing a robust paradigm for hybrid retrieval.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
