Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning

TL;DR

This paper presents a reinforcement learning-based conversational agent that dynamically interleaves search and reasoning across multiple dialogue turns, improving multi-turn human-AI interactions.

Contribution

It introduces a novel RL-trained agent capable of adaptive, multi-turn reasoning and search, surpassing static pipeline approaches and single-turn methods.

Findings

Outperforms existing baselines on four conversational benchmarks.

Demonstrates effective multi-turn reasoning and search integration.

Enhances adaptability in evolving user goal scenarios.

Abstract

Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the context-dependent user intent evolves across interactions, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Existing studies usually follow static rewrite, retrieve, and generate pipelines, which optimize different procedures separately and overlook the mixed-initiative action optimization simultaneously. Although the recent developments in deep search agents demonstrate the effectiveness in jointly optimizing retrieval and generation via reasoning, these approaches focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods by surpassing several existing strong baselines.