# Multi-Step Query Rewriting Agent

The work recasts conversational query rewriting as a sequential retrieval problem in which an agent chooses among intent resolution, lexical reformulation, and pseudo-document synthesis, conditioning each rewrite on passages returned by the previous step, and is trained by supervised fine-tuning plus reinforcement learning against retrieval quality alone with no human rewrite annotations; it achieves the highest MRR and NDCG@3 on TopiOCQA and QReCC and transfers zero-shot to TREC CAsT and to dense retrieval backends.

The work recasts conversational query rewriting as a sequential retrieval problem in which an agent chooses among intent resolution, lexical reformulation, and pseudo-document synthesis, conditioning each rewrite on passages returned by the previous step, and is trained by supervised fine-tuning plus reinforcement learning against retrieval quality alone with no human rewrite annotations; it achieves the highest MRR and NDCG@3 on TopiOCQA and QReCC and transfers zero-shot to TREC CAsT and to dense retrieval backends.