AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

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 Integrity, a deployment reliability criterion for evaluating whether the computation recorded behind an answer is explicit, executable, schema-valid, operator-faithful, replayable, answer-consistent, and auditable. We identify the Structure Gap as the deployment failure mode that makes Trace Integrity necessary: natural-language reasoning and free-form rationales do not reliably specify the operator-leve

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T09:11:58.312Z. This is not the publication date.