When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs

arXiv:2606.28438 · cs.SE, cs.AI · Submitted 2026-06-26 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-06-26

Updated: 2026-10-12

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties