SkillForge: Compositional Skill Synthesis with Verification-in-the-Loop for Generating Formally Verified Dafny Programs

SkillForge is a framework that breaks down formal code synthesis into reusable atomic skills, each handling a specific subtask such as specification inference, body synthesis, invariant generation, error diagnosis, or repair. A verification-driven harness coordinates these skills by submitting candidates to the Dafny verifier, diagnosing failures, and routing them deterministically to the appropriate repair skill until correctness is achieved or a budget is reached. On a curated benchmark, SkillForge outperforms state‑of‑the‑art agentic and iterative baselines, requiring fewer tokens and lower latency, with ablation studies showing each skill’s measurable contribution and rapid convergence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• agents
• reinforcement-learning
• benchmarks