Retrieval-Augmented Generation vs. Chain-of-Thought Prompting for Zero-Shot Anomaly Detection in Time-Series CPS Data

This report synthesises findings from 7 peer-reviewed papers addressing the following research question: How does retrieval-augmented generation compare to chain-of-thought prompting in improving zero-shot anomaly detection accuracy for open-weight LLMs on time-series CPS datasets. 11 claims were extracted from source literature; 11 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does retrieval-augmented generation compare to chain-of-thought prompting in improving zero-shot anomaly detection accuracy for open-weight LLMs on time-series CPS datasets?

Autonomous literature synthesis. Automated review score: 8.3/10. Full text and citation available at Assignee Research.