让搜索代理自我进化，更准更快找信息。
SE-Search: Self-Evolving Search Agent via Memory and Dense Reward
- 用记忆净化、原子查询训练和密集奖励提升搜索能力
- 单跳和多跳问答任务上性能比基线高10.8分
- 适合需要精准信息检索的AI系统开发者
检索增强生成（RAG）通过引入外部知识减少大语言模型的幻觉和事实错误。近期的搜索代理将RAG转化为自主的多轮信息检索过程。然而，现有方法常积累无关或噪声文档，且依赖稀疏强化学习信号。我们提出自进化搜索（SE-Search），通过三个组件改进在线搜索行为：记忆净化、原子查询训练和密集奖励。SE-Search采用“思考-搜索-记忆”策略，保留关键证据并过滤冗余内容。原子查询训练促进更短、更多样化的查询，提升证据获取效率。密集奖励提供细粒度反馈，加速训练。在单跳和多跳问答基准测试中，SE-Search-3B模型显著优于强基线，在绝对性能上提升10.8点，相对增益达33.8%，超越Search-R1。
原文摘要 · Abstract (English)
Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn information-seeking process. However, existing methods often accumulate irrelevant or noisy documents and rely on sparse reinforcement learning signals. We propose \textbf{S}elf-\textbf{E}volving \textbf{Search}, a Self-Evolving Search agent that improves online search behavior through three components, memory purification, atomic query training, and dense rewards. SE-Search follows a \textit{Think-Search-Memorize} strategy that retains salient evidence while filtering irrelevant content. Atomic query training promotes shorter and more diverse queries, improving evidence acquisition. Dense rewards provide fine-grained feedback that speeds training. Experiments on single-hop and multi-hop question answering benchmarks show that \texttt{SE-Search-3B} outperforms strong baselines, yielding a $10.8$ point absolute improvement and a $33.8\%$ relative gain over Search-R1.\footnote{We will make the code and model weights publicly available upon acceptance.}
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。