arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.31377cs.IRcs.AI
收藏

DynaTree: 面向时效性新闻检索的动态智能检索树

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval

Shanghai Jiao Tong University(上海交通大学)

Siyuan Qi, Xinyuan Wang, Yingxuan Yang, Haochuan Guo, Jianghao Lin, Weiwen Liu, Yong Yu, Weinan Zhang

AI总结:

提出DynaTree两阶段框架,通过离线构建可复用检索树和在线轻量子树选择,实现高效、自适应的时效性新闻检索,在Syft新闻基准和BEIR数据集上优于标准RAG和现有智能体方法。

摘要:

智能体检索增强生成通过集成规划、工具使用和迭代推理改进了检索,但现有的智能体RAG方法通常将语义扩展与检索决策耦合在短视推理循环中,导致推理成本高且不适用于时效性新闻检索。我们提出DynaTree,一个高效自适应新闻检索的两阶段框架。在离线阶段,DynaTree使用协调的智能体构建一个可复用的检索树,具体化查询主题的语义空间。在在线阶段,DynaTree在时间局部评估代理上执行轻量级日常子树选择,无需进一步的智能体推理、树修改或重新训练。在多日Syft新闻基准和多个BEIR数据集上的实验表明,DynaTree实现了强大的召回和排序性能,始终优于标准RAG和先前的智能体基线。我们进一步在Syft生产系统中部署DynaTree,并通过2026年1月28日至2月6日的在线A/B测试进行评估。动态适应变体将固定离线选择子树的生存率从0.32-0.53提高到0.59-0.73,并且在每个评估日都优于现有的生产召回器。这些结果表明,持久的、结构感知的语义扩展可以将离线智能体推理转化为实际改进,覆盖范围、新鲜度和相关性在真实世界新闻检索中均得到提升。

英文摘要:

Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods often couple semantic expansion with retrieval decisions in short-horizon inference loops, leading to high inference cost and limited suitability for time-sensitive news retrieval. We propose DynaTree, a two-stage framework for efficient and adaptive news retrieval. In the offline stage, DynaTree uses coordinated agents to construct a reusable retrieval tree that materializes the semantic space of a query topic. In the online stage, DynaTree performs lightweight daily subtree selection over a time-localized evaluation proxy, without further agentic reasoning, tree modification, or retraining. Experiments on a multi-day Syft news benchmark and multiple BEIR datasets show that DynaTree achieves strong recall and ranking performance, consistently outperforming standard RAG and prior agentic baselines. We further deploy DynaTree in the Syft production system and evaluate it through online A/B testing from Jan. 28 to Feb. 6, 2026. The dynamically adapted variant improves survival rate from 0.32-0.53 to 0.59-0.73 over a fixed offline-selected subtree and outperforms existing production recallers on every evaluation day. These results show that persistent, structure-aware semantic expansion can translate offline agentic reasoning into practical improvements in coverage, freshness, and relevance for real-world news retrieval.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑