斯坦福 RAG 新架构：用 Jev 一次打分 20 个候选段落
斯坦福团队提出检索、Jev、agent 一体的 RAG 循环：一次 Jev 请求给 20 个候选段落打分并做可答性、注入两道门控，只放行 0.6 以上的段落，再用第二次 Jev 校验引用。
this is pure f*cking treasure A Stanford AI research group finally drew the perfect RAG system: retrieval, Jev and agents in one loop, and it fixes the 3 things that break every RAG app: > the LLM reads 20 passages when only 3 matter > it answers questions your docs can't answer > it trusts whatever text it retrieves here's how it runs: > a lead agent sends the query > hybrid search pulls the top 20 candidates, dense + keyword > ONE Jev request scores all 20 + 2 gates: answerable? injection? > only passages above 0.6 reach the writer agent > a second Jev call checks every claim against its source > grounded answer, with citations and when the docs don't have it: > answerable fails, the writer never runs > a researcher agent rewrites the query and retries once > still nothing? "not in the docs". zero tokens spent on a guess retrieval casts the net. Jev decides what's real. agents do the work save this before you build your next RAG
这条是引用着另一条写的：x.com/n01ennn/status/2103542021071978601