ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization

arXiv:2605.16299v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement. Recent solver--verifier frameworks exploit program execution as an automatic supervision signal, but their effectiveness degrades as solvers become moderately strong: verifier-generated tests increasingly confirm semantic correct