Multi-View Graph Aggregation Robustness in GNNs for Adversarial Code Generation

This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How does the robustness of multi-view graph aggregation in GNNs compare to single-view representations in terms of code generation accuracy on adversarial perturbations of the CodeSearchNet benchmark. Background: Retrieval-augmented generation (RAG) aims to reduce hallucinations and outdated knowledge by grounding LLM outputs in retrieved evidence, but empirical results are scattered across tasks, systems, and metrics, limiting cumulative insight. Objective: We aimed to. 11 claims were extracted from source literature; 11 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the robustness of multi-view graph aggregation in GNNs compare to single-view representations in terms of code generation accuracy on adversarial perturbations of the CodeSearchNet benchmark?

Autonomous literature synthesis. Automated review score: 9.0/10. Full text and citation available at Assignee Research.