AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models

Computer Science > Artificial Intelligence [Submitted on 3 Apr 2026] AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models Yuntao Du, Minh Dinh, Kaiyuan Zhang, Ninghui Li Scientific and Technical Intelligence (S&TI) analysis requires verifying complex technical claims across rapidly growing literature, where existing approaches fail to bridge the verification gap between surface-level accuracy and deeper methodological validity. We present AutoVerifier, an LLM-based agentic framework that automates end-to-end verification of technical claims without requiring domain expertise. AutoVerifier decomposes every technical assertion into structured claim triples of the form (Subject, Predicate, Object), constructing knowledge graphs that enable structured reasoning across six progressively enriching layers: corpus construction and ingestion, entity and claim extraction, intra-document verification, cross-source verification, external signal corroboration, and final hypothesis matrix generation. We demonstrate AutoVerifier on a contested quantum computing claim, where the framework, operated by analysts with no quantum expertise, automatically identified overclaims and metric inconsistencies within the target paper, traced cross-source contradictions, uncovered undisclosed commercial conflicts of interest, and produced a final assessment. These results show that structured LLM verification can reliably evaluate the validity and maturity of emerging technologies, turning raw technical documents into traceable, evidence-backed intelligence assessments. Comments: Winner of 2025-2026 Radiance Technologies Innovation Bowl Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Information Retrieval (cs.IR); Machine Learning (cs.LG); Social and Information Networks (cs.SI) Cite as: arXiv:2604.02617 [cs.AI]   (or arXiv:2604.02617v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.02617 Focus to learn more Submission history From: Yuntao Du [view email] [v1] Fri, 3 Apr 2026 01:11:43 UTC (20 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CR cs.IR cs.LG cs.SI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)