PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans

  • 类型:arxiv
  • 标识:2608.26091
  • 链接:http://arxiv.org/abs/2608.26091v1
  • 主分类:rag
  • 形态:benchmark
  • 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:A Visual-First Multimodal Retrieval-Augmented Generation (RAG) framework called PlanSightRAG, which indexes and reasons directly over plan imagery, integrates a ColNomic-3B multi-vector retrieval, an agentic Planner-Retriever-Auditor-Synthesizer, and MaxSim heatmaps as an evidence trail.
  • OpenAlex ID:W7204441260
  • OpenAlex DOI:10.48550/arxiv.2608.26091
  • DOI:10.48550/arxiv.2608.26091
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/2608.26091
  • OpenAlex更新:2026-09-01
  • 副分类:multimodal
  • 待LLM分类:否
  • 标题中文:PlanSightRAG:面向土木标准图自动化问答与合规审查的视觉优先多模态 RAG
  • TLDR中文:PlanSightRAG 是一种 Visual-First 多模态 RAG 框架,直接对图纸图像建立索引并进行推理,集成了 ColNomic-3B 多向量检索、Agentic Planner-Retriever-Auditor-Synthesizer,并以 MaxSim 热力图作为证据链。
  • 来源文件:
  • /inbox/tom/_candidates/2026-08-27-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-28-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]