Codestral and DeepSeek R1 Self-Repair Robustness Under NESTFUL Adversarial Perturbations

This report synthesises findings from 4 peer-reviewed papers addressing the following research question: How does the robustness of Codestral and DeepSeek R1's self-repair vary against adversarial perturbations in NESTFUL nested sequences, measured by completion accuracy drop. Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from both academia and industry. However, as new and improved LLMs are developed, existing evaluation benchmarks (e.g., HumanEval, MBPP) are no. 7 claims were extracted from source literature; 7 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the robustness of Codestral and DeepSeek R1's self-repair vary against adversarial perturbations in NESTFUL nested sequences, measured by completion accuracy drop?

Autonomous literature synthesis. Automated review score: 9.2/10. Full text and citation available at Assignee Research.