DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation

  • 类型:arxiv
  • 标识:2607.06507
  • 链接:http://arxiv.org/abs/2607.06507v1
  • 主分类:rag
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:DynaKRAG is introduced, which formulates multi-hop evidence acquisition as state-conditioned control over atomic evidence operations, and demonstrates the benefit of coordinating retrieval, diagnosis, and gap-directed acquisition under an evolving evidence state.
  • OpenAlex ID:W7167739248
  • OpenAlex DOI:10.48550/arxiv.2607.06507
  • DOI:10.48550/arxiv.2607.06507
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.06507
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:DynaKRAG:面向多跳检索增强生成的可学习证据控制统一框架
  • TLDR中文:提出 DynaKRAG,将多跳证据获取建模为针对原子证据操作的状态条件控制,并展示了在演化证据状态下协同检索、诊断与缺口定向获取的优势。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-08-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]