TechGraphRAG: An Agentic Graph-Augmented RAG Framework for Technical Literature Reasoning
2026-06-01 • Information Retrieval
Information RetrievalArtificial IntelligenceMultiagent Systems
AI summaryⓘ
The authors developed a smart system that helps with technical reasoning by searching and understanding a large collection of academic papers about intelligent tires and vehicle control. Unlike simpler systems that do one search, their system goes through 13 steps to check if the information found is enough, can improve searches if needed, and verifies sources carefully. They also use a knowledge graph to see how ideas relate to each other and have built-in quality checks to make sure the answers are reliable. This approach helps people explore and reason about complex technical topics more effectively.
retrieval-augmented generationknowledge graphacademic search databasesquery classificationevidence sufficiency scoringcitation verificationtechnical reasoningagentic retryLLM (Large Language Model)vehicle dynamics
Authors
Kanwar Bharat Singh
Abstract
This paper presents an agentic retrieval-augmented generation (RAG) framework for domain-specific technical reasoning support, instantiated over a curated corpus of approximately 2,100 academic papers in intelligent tires, vehicle dynamics, and vehicle control. Unlike conventional single-pass RAG systems, the proposed architecture employs a 13-step autonomous pipeline that classifies queries by intent, scores evidence sufficiency against a multi-dimensional rubric, performs agentic retry with drift-guarded query reformulation, searches external academic databases (Crossref, OpenAlex, Semantic Scholar) through iterative optimize--search--vet loops, traverses a Neo4j knowledge graph for relational context, verifies citation integrity, and applies post-generation quality checks with automatic regeneration. Key contributions include a 100-point evidence sufficiency scoring framework across five dimensions with relevance damping and hybrid rule-based/LLM review; a route-dependent external search architecture with iterative agentic loops; a knowledge graph constructed via LLM-based entity extraction and OpenAlex author validation with intra-corpus citation resolution; and a self-correcting generation loop with citation verification and quality assessment. The framework is presented as a practical, implemented case study illustrating how agentic, evidence-grounded RAG can support literature navigation and technical reasoning over large, domain-specific corpora.