Score: 2

ATLAS: Automated Toolkit for Large-Scale Verified Code Synthesis

Published: December 11, 2025 | arXiv ID: 2512.10173v1

By: Mantas Baksys , Stefan Zetzsche , Olivier Bouissou and more

BigTech Affiliations: Amazon

Potential Business Impact:

Creates code that checks itself for mistakes.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Large language models have shown potential for program verification, but progress is hindered by the scarcity of verified code for training. We present ATLAS, an automated pipeline that synthesizes verified programs at scale to address this data bottleneck. ATLAS generates complete Dafny programs with specifications, implementations, and proofs, producing 2.7K verified programs from which we extract over 19K training examples--more than 7 per verified program--by decomposing the synthesis process into multiple specialized tasks. Fine-tuning Qwen 2.5 7B Coder on this dataset produces substantial gains: +23 percentage points on DafnyBench and +50 percentage points on DafnySynthesis. These results demonstrate that synthetic verified code can effectively enhance LLM capabilities for formal verification.

Country of Origin
πŸ‡¬πŸ‡§ πŸ‡ΊπŸ‡Έ United Kingdom, United States

Page Count
9 pages

Category
Computer Science:
Software Engineering