From Verification Failures to Reusable Guidance for Coding Agents

The paper presents a method for turning expert diagnoses of verification failures into reusable guidance for coding agents. By combining executable language definitions in the K framework with a set of procedures for constructing specifications, repairing proofs, and auditing their adequacy, the authors achieve a 164/164 success rate on the HumanEval benchmark after two targeted repairs. They further demonstrate that audits can detect defects missed by successful proofs and evaluate the approach on KleverBench and Optimism proofs, highlighting both progress and remaining challenges.

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 AI.

• agents
• benchmarks