SolidCoder: Don't Imagine, Execute — State-of-the-Art Code Gen via Sandboxed Verification

arXiv·medium signal

Addresses the 'Mental-Reality Gap' where LLMs hallucinate execution traces during code generation. SolidCoder's S.O.L.I.D. architecture forces edge-case awareness before algorithm design and replaces imagined traces with sandboxed execution using property-based oracles. With GPT-4o achieves 95.7% pass@1 on HumanEval, 77.0% on CodeContests (+4.3pp), 26.7% on APPS (+3.4pp).