[2603.21018] DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning

Computer Science > Information Retrieval arXiv:2603.21018 (cs) [Submitted on 14 Jan 2026] Title:DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning Authors:Yunhai Hu, Junwei Zhou, Yumo Cao, Yitao Long, Yiwei Xu, Qiyi Jiang, Weiyao Wang, Xiaoyu Cao, Zhen Sun, Yiran Zou, Nan Du View a PDF of the paper titled DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning, by Yunhai Hu and 10 other authors View PDF HTML (experimental) Abstract: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, consiste...