12,445 papers · continuously updated · last export: 10 Aug 2026livingmeta.ai
← Browse all papers
AI evidence extraction

TechRAG: Evidence-Gated Multimodal Agentic RAG for Technical Literature Reasoning

Kanwar Bharat Singh · arXiv (Cornell University) · 2026

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10
Relevance
0/4
Quality (LMQS)
D
Evidence
0
Citations

This is an AI analysis. Read the peer-reviewed original at the publisher: https://doi.org/10.48550/arxiv.2606.01613

Methodology & findings

Study design

Artifact design and implementation.

Primary method

Design science (system design and implementation of a retrieval-augmented generation framework with multiple integrated subsystems)

Main result

The framework presents a practical, evidence-gated multimodal agentic RAG architecture with key contributions including "a scalable multimodal retrieval architecture combining text, graph, and visual evidence over 40,000 document pages; (ii) an interpretable evidence sufficiency and retry mechanism; (iii) a multi-agent generation pipeline with evidence mapping and critic-driven revision; (iv) a domain knowledge graph with LLM-based entity extraction, OpenAlex author validation, and intra-corpus citation resolution; and (v) a route-dependent external search architecture for targeted literature expansion."

Research paradigm

Design science / Systems engineering

Author conclusions

The authors present "a practical, evidence-gated, multimodal agentic RAG architecture for technical reasoning over specialized research corpora" as their instantiation on a domain-specific corpus of "several thousand papers in intelligent tires, vehicle dynamics, vehicle control, sensing, estimation, and machine learning."

Data: not_statedCode: not_statedExtracted from: pdfAgreement 83%

Explore related topics

RAG for ResearchLiterature DiscoveryDesign Science

Related papers

← Browse all papers