Hydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support

arXiv:2605.15238v1 Announce Type: cross Abstract: Large language models are increasingly used for code generation, but many generated programs fail to compile, a prerequisite for further correctness checks such as unit tests. Existing solutions for repairing static errors are costly in both latency and token consumption. Post-hoc repair delays error detection until generation completes and commonly regenerates large regions of previously valid code. Constrained semantic decoding checks after eac