ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering

• URL: http://arxiv.org/abs/2510.13312v1
• Date: Wed, 15 Oct 2025 09:00:20 GMT
• Title: ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering
• Authors: Simon Lupart, Mohammad Aliannejadi, Evangelos Kanoulas,
• Abstract summary: We present ChatR1, a reasoning framework based on reinforcement learning (RL) for conversational question answering (CQA)<n>ChatR1 interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through RL.<n>Our proposed ChatR1 demonstrates strong performance on both 3B and 7B model backbones, outperforming competitive models on five CQA datasets.
• Score: 30.81641818112445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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. Our proposed 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-sensitive behavior than static CQA pipelines.

Related papers

• Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning [66.52010873968383]
  We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training.<n>The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods.
  arXiv  Detail & Related papers  (2026-01-19T14:55:54Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning [74.65632662894086]
  We propose ReSearch, a framework that trains LLMs to Reason with Search via reinforcement learning.<n>Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking.<n>Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction.
  arXiv  Detail & Related papers  (2025-03-25T09:00:58Z)
• CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation [68.81271028921647]
  We introduce CORAL, a benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from Wikipedia. It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling.
  arXiv  Detail & Related papers  (2024-10-30T15:06:32Z)
• AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment [16.62505706601199]
  We present a novel framework AdaCQR for conversational search reformulation.<n>By aligning reformulation models with both term-based and semantic-based retrieval systems, AdaCQR enhances the generalizability of information-seeking queries.<n> Experimental results on the TopiOCQA and QReCC datasets demonstrate that AdaCQR outperforms the existing methods in a more efficient framework.
  arXiv  Detail & Related papers  (2024-07-02T05:50:16Z)
• Response Enhanced Semi-supervised Dialogue Query Generation [40.17161986495854]
  We propose a semi-supervised learning framework -- SemiDQG -- to improve model performance with unlabeled conversations. We first apply a similarity-based query selection strategy to select high-quality RA-generated pseudo queries. We adopt the REINFORCE algorithm to further enhance QP, with RA-provided rewards as fine-grained training signals.
  arXiv  Detail & Related papers  (2023-12-20T02:19:54Z)
• FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems [53.89014188309486]
  We present a flexible neural framework that can integrate contextual information from multiple channels. We evaluate our model on the MSDialog dataset widely used for evaluating conversational response ranking tasks.
  arXiv  Detail & Related papers  (2023-03-31T23:58:28Z)
• CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning [16.470428531658232]
  We develop a query rewriting model CONQRR that rewrites a conversational question in context into a standalone question. We show that CONQRR achieves state-of-the-art results on a recent open-domain CQA dataset.
  arXiv  Detail & Related papers  (2021-12-16T01:40:30Z)
• Conversational Query Rewriting with Self-supervised Learning [36.392717968127016]
  Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem by explicitly rewriting the conversational query into a self-contained utterance. Existing approaches rely on massive supervised training data, which is labor-intensive to annotate. We propose to construct a large-scale CQR dataset automatically via self-supervised learning, which does not need human annotation.
  arXiv  Detail & Related papers  (2021-02-09T08:57:53Z)
• CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation [62.13413129518165]
  CR-Walker is a model that performs tree-structured reasoning on a knowledge graph. It generates informative dialog acts to guide language generation. Automatic and human evaluations show that CR-Walker can arrive at more accurate recommendation.
  arXiv  Detail & Related papers  (2020-10-20T14:53:22Z)
• Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues [88.73739515457116]
  We introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination. We jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner. Experiment results indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection.
  arXiv  Detail & Related papers  (2020-09-14T08:44:46Z)
• Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting [56.268862325167575]
  We tackle conversational passage retrieval (ConvPR) with query reformulation integrated into a multi-stage ad-hoc IR system. We propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model.
  arXiv  Detail & Related papers  (2020-05-05T14:30:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.