WybeCoder: Verified Imperative Code Generation
This addresses the gap in automated software verification for imperative code, enabling systematic evaluation and dataset creation, though it builds incrementally on existing verification frameworks.
The authors tackled the problem of software verification lagging behind code generation by proposing WybeCoder, a framework for verified imperative code generation that achieved 74% success on Verina tasks and 62% on Clever tasks, synthesizing hundreds of lines of verified code.
Recent progress in large language models (LLMs) has advanced automatic code generation and formal theorem proving, yet software verification has not seen the same improvement. To address this gap, we propose WybeCoder, an agentic code verification framework that enables prove-as-you-generate development where code, invariants, and proofs co-evolve. It builds on a recent framework that combines automatic verification condition generation and SMT solvers with interactive proofs in Lean. To enable systematic evaluation, we translate two benchmarks for functional verification in Lean, Verina and Clever, to equivalent imperative code specifications. On complex algorithms such as Heapsort, we observe consistent performance improvements by scaling our approach, synthesizing dozens of valid invariants and dispatching of dozens of subgoals, resulting in hundreds of lines of verified code, overcoming plateaus reported in previous works. Our best system solves 74% of Verina tasks and 62% of Clever tasks at moderate compute budgets, significantly surpassing previous evaluations and paving a path to automated construction of large-scale datasets of verified imperative code.