arXiv:2609.37603v1 Announce Type: cross
Abstract: A common safeguard for a data pipeline is redundant computation: derive each published number by two routes built on different technology and refuse...
By Fabio Rovai
arXiv:2605. 26874v2 Announce Type: replace-cross Abstract: LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores.
By Madhulatha Mandarapu, Sandeep Kunkunuru
arXiv:2607. 25959v1 Announce Type: cross Abstract: Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation.
By Fanfu Wei, Thibault Ehrhart, Rapha\"el Troncy
Answer accuracy is an insufficient reliability signal for LLM data agents. In structured-data tasks, a benchmark-correct answer can be produced by an invalid trace. This paper introduces Trace Integri...
The paper argues that answer accuracy alone is insufficient for evaluating large language model (LLM) data agents, especially in structured-data tasks where a correct answer can be produced by an invalid trace. It introduces Trace Integrity as a reliability criterion that ensures the computation behind an answer is explicit, executable, schema-valid, operator-faithful, replayable, answer-consistent, and auditable. The authors operationalize this concept with execution contracts and present the CAIT (Correct Answer / Invalid Trace) Rate to quantify how often answer-only evaluations mistakenly reward unsupported outputs, demonstrating that accuracy, trace validity, and silent-failure risk are distinct signals.
By Srimonti Dutta, Akshata Kishore Moharir
arXiv:2607. 03447v1 Announce Type: cross Abstract: Knowledge graphs (KGs) that underpin Graph-based Retrieval-Augmented Generation (Graph-RAG) are increasingly built automatically by LLM-driven extraction rather than curated by experts.
By Axel TahmasebiMoradi, Lucas Schott, Martin Royer