paper-with-me

홈 › Papers

AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models

2026-04-03 · Yuntao Du, Minh Dinh, Kaiyuan Zhang, Ninghui Li arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.02617

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Similar Papers 제목 키워드 기반

AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification

2026-08-26 · Zebei Zhao, Zhihao Shi, Minqi Shi arxiv

Reference-based verifiers are important for evaluating reasoning models and providing accurate outcome rewards in reinforcement learning with verifiable rewards. To improve verification accuracy, prior work has explored …

Reinforcement Learning

Agentic Proving for Program Verification

2026-05-22 · Alessandro Sosso, Akhil Arora, Bas Spitters arxiv

Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an…

Automated Theorem ProvingCode Generation

BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature

2026-01-12 · Peiran Li, Fangzhou Lin, Shuo Xing, Xiang Zheng 외 arxiv

Citations are the bedrock of scientific authority, yet their integrity is compromised by widespread miscitations: ranging from nuanced distortions to fabricated references. Systematic citation verification is currently u…

MIND: AI Co-Scientist for Material Research

2026-04-15 · Geonhee Ahn, Donghyun Lee, Hayoung Doo, Jonggeol Na 외 arxiv

Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning without automated experimental verification. We propose MIND, an LLM-driven…

From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification

2026-06-11 · Rongxin Yang, Shenghong He, Siyuan Zhu, Chao Yu arxiv

Recent approaches combining Large Language Models (LLMs) with retrieval-augmented reasoning have shown promise for automated fact verification. To process complex claims, these verification pipelines typically execute mu…

Reinforcement LearningFact VerificationAnswer Generation