让AI理解复杂问题并动态搜索信息，提升问答准确率。
QAgent: A modular Search Agent with Interactive Query Understanding
- 用强化学习训练可交互的搜索代理，动态优化查询理解
- 在多个数据集上问答准确率显著超越传统RAG方法
- 模块化设计适合嵌入真实系统，部署灵活易扩展
大型语言模型（LLMs）在自然语言任务中表现优异，但受限于静态参数化知识，尤其在知识密集型任务中表现不足。检索增强生成（RAG）通过引入外部信息缓解此问题。然而，传统RAG在复杂查询理解方面存在困难；即便使用强化学习（RL）训练的搜索代理，仍面临泛化能力差和部署难的问题。为此，我们提出QAgent，一个统一的智能体式RAG框架，采用搜索代理实现自适应检索。该代理通过交互式推理与检索，不断优化对查询的理解。为支持实际应用，我们设计了模块化搜索代理，具备即插即用特性，适用于复杂系统。具体而言，代理遵循多步决策流程，通过强化学习训练以最大化检索质量，从而支持下游任务的精准回答。我们进一步分析了端到端强化学习的优劣，并提出聚焦有效检索的策略，显著提升了LLM应用的泛化能力。实验表明，QAgent在问答任务中表现卓越，且可作为即插即用模块用于真实场景部署。
原文摘要 · Abstract (English)
Large language models (LLMs) excel at natural language tasks but are limited by their static parametric knowledge, especially in knowledge-intensive task. Retrieval-augmented generation (RAG) mitigates this by integrating external information. However, (1) traditional RAG struggles with complex query understanding, and (2) even search agents trained with reinforcement learning (RL), despite their promise, still face generalization and deployment challenges. To address these limitations, we propose QAgent, a unified agentic RAG framework that employs a search agent for adaptive retrieval. This agent optimizes its understanding of the query through interactive reasoning and retrieval. To facilitate real-world application, we focus on modular search agent for query understanding that are plug-and-play in complex systems. Secifically, the agent follows a multi-step decision process trained with RL to maximize retrieval quality and support accurate downstream answers. We further analyze the strengths and weaknesses of end-to-end RL and propose a strategy that focuses on effective retrieval, thereby enhancing generalization in LLM applications. Experiments show QAgent excels at QA and serves as a plug-and-play module for real-world deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。