English(EN)Search, Inspect, Fetch: Exploiting Boolean Retrieval for Deep-Research Agents
新研究通过结构化检索和评分标准排名增强AI代理 · 跟踪4个来源
作者PulseAugur 编辑部·[7 个来源]·
两篇新研究论文介绍了增强AI代理信息处理能力的创新方法。第一篇论文《搜索、检查、获取》提出了SIEVE接口，该接口利用字段化布尔检索（BQL）使代理能够将搜索限制在特定文档字段，从而提高准确性并减少令牌使用。第二篇论文《使用搜索评分标准训练文档重排序器》介绍了RubricRanker，一种使用LLM合成的搜索评分标准进行训练的文档重排序器，以确保检索到的文档集满足复杂的信息需求，在深度研究和RAG基准测试中表现优于基线。
AI
arXiv:2601.12369v5 Announce Type: replace Abstract: Deep Research Agents increasingly automate survey writing, yet existing benchmarks do not jointly test whether they retrieve the papers experts consider essential and organize those papers into paper-grounded taxonomies. We intr…
arXiv:2608.03527v1 Announce Type: cross Abstract: Retrieval systems help deep research agents generate high-quality answers by providing relevant documents. However, existing retrievers typically select documents through relevance matching, while individually well-matched top-$k$…
arXiv:2608.02751v1 Announce Type: cross Abstract: Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web sources expose through titles, headings, sections, and metadata. This prevents …
Retrieval systems help deep research agents generate high-quality answers by providing relevant documents. However, existing retrievers typically select documents through relevance matching, while individually well-matched top-$k$ documents may not form a \textit{set} that satisf…
Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web sources expose through titles, headings, sections, and metadata. This prevents agents from directly constraining retrieval to doc…
Existing deep-research agents use a Search--Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata. This prevents agents from directly constraining retrieval to parts of a webpage and often carri…
Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web sources expose through titles, headings, sections, and metadata. This prevents agents from directly constraining retrieval to doc…
