站内快照 · 国内可打开。外网原文可能无法访问。

• 论文公开站arXiv2026年10月8日 22:11

  RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing

  Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adapt queries and tool use but remain largely retrieva

  原文链接