Conversational information seeking (CIS) systems aim to model the user’s information need within the conversational context and retrieve the relevant information. One major approach to modeling the conversational context aims to rewrite the user utterance in the conversation to represent the information need independently. In this work, we hypothesize that breaking down the information of an utterance into multiple queries covering different aspects of the information need can lead to more effective retrieval performance. This is more evident in more complex utterances that require gathering evidence from various information sources, where a single query rewrite or query representation cannot capture the complexity of the utterance. We propose MQ4CS, a multi-aspect query generation and retrieval framework, which uses Large Language Models (LLMs) to break the user utterance into multiple queries. This approach improves retrieval performance, as most utterances benefit from more than one rewritten query. We evaluate MQ4CS on six widely used CIS datasets, showing it outperforms state-of-the-art query rewriting methods. Using MQ4CS, we also construct MASQ, which includes multiple-aspect queries for the six datasets. Fine-tuning the model on MASQ yields significant improvements. We make our code and dataset publicly available.

We present ChatR1, a reasoning framework based on reinforcement learning (RL) for conversational question answering (CQA). Reasoning plays an important role in CQA, where user intent evolves across dialogue turns, and utterances are often underspecified, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Unlike static ‘rewrite, retrieve, and generate’ pipelines, ChatR1 interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through RL. To address the challenge of sparse and delayed rewards in RL, we propose an intent-aware reward that provides turn-level feedback by aligning retrieval and reasoning with evolving user goals. ChatR1 demonstrates strong performance on both 3B and 7B model backbones, outperforming competitive models on five CQA datasets, measured by different metrics (F1, BERTScore, and LLM-as-judge). We include a diverse set of CQA datasets to cover topic shifts, evolving intents, mixed-initiative dialogues, and multi-document grounding, testing ChatR1’s performance from various aspects. Ablation studies confirm the effectiveness of the intent-aware reward. Our analyses further reveal diverse reasoning trajectories and effective use of the search tool. ChatR1 also generalizes robustly across domains, demonstrating that RL-based reasoning enables more flexible and context-aware behavior than static CQA pipelines.