论文arxiv cs.CL · 1d ago需要关注

LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation

分类释义:学术论文 / 技术报告

TL;DR

arXiv:2607.27353v1 Announce Type: new Abstract: Agentic retrieval-augmented generation systems can produce answers that appear grounded while failing at the evidence, tool-contract, authorization, or session-state layer. We introduce LayerRAG-Bench, a controlled cross-layer reliability benchmark with 8 enterprise domains, 240 tasks, 9 fault scenarios, 2 contract modes, and 38,880 live task-level records across nine models from OpenAI, Anthropic, and Gemini. Schema normalization raises schema-dri

关键要点

  • 01arXiv:2607.27353v1 Announce Type: new Abstract: Agentic retrieval-augmented generation systems can produce answers that appear grounded while failing at the evidence
  • 02tool-contract
  • 03authorization
  • 04or session-state layer. We introduce LayerRAG-Bench
为什么值得关注

对你的工程实践意味着什么

LLM 实时生成MiniMax-M2.7
角色你应该做什么
Tech Lead评估 LayerRAG-Bench 的故障分类体系,纳入 Agentic RAG 系统的技术选型标准
应用工程师查阅 9 种 fault scenarios 的具体定义,在开发中针对性设计防御性检查
运维 / 平台暂无直接影响,了解即可
产品 / 业务暂无直接影响,了解即可
阅读原文 ↗来源:arxiv cs.CL

同类资讯

本页 TL;DR 与「为什么」由 LLM 生成 · 模型:MiniMax-M2.7 / Claude Haiku 4.5