DVCQR: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement Learning

Conversational query rewriting (CQR) addresses context dependence in conversational search by rewriting each user query into a standalone form. Recent approaches leverage reinforcement learning (RL) to directly optimize retrieval effectiveness; however, they typically rely on a single rewrite, which struggles to accommodate the divergent preferences of sparse and dense retrievers and often suffers from conflicting optimization signals. We propose DVCQR, a Dual-View CQR framework that explicitly generates two complementary rewrites for each query: a sparse-view rewrite that emphasizes distinctive lexical anchors, and a dense-view rewrite that captures complete semantic constraints. Both rewrites are produced in a single pass via a structured reasoning process. To further mitigate objective conflicts, we introduce a stage-wise RL strategy that sequentially aligns the sparse and dense views with their corresponding retrievers using rankbased feedback. Extensive experiments on four benchmarks (TopiOCQA, QReCC, demonstrate that DVCQR consistently outperforms state-of-the-art methods on most metrics under both sparse and dense retrieval settings, validating the effectiveness of dual-view rewriting and stage-wise retriever alignment.