Skip to content
NewA calmer, faster ZeroHour

AuXSpec trains Lean specification models with executable rewards

Original title: AuXSpec: Learning to Autoformalize Program Specifications via Executable Postconditions

Hugging Face daily papersby Haocheng Wang, Weixuan Yuan, Florian Hübler ()1 min read
AI summary · x-ai/grok-4.7Summaries by Vani AI

Authors release trained Qwen3.5-9B and Qwen3.8-27B weights; the 27B model led SpecGen pass@4 at 84.3%.

AuXSpec is a Lean framework that pairs declarative postconditions with executable counterparts so test cases can score specifications by execution and supply a reinforcement-learning reward. The authors synthesized 3,037 LeetCode problems and expanded training to 19.5K samples via expert iteration on Codeforces. They report that training Qwen3.5-9B and Qwen3.8-27B raised SpecGen pass@4 on AuXSpec-Test from 0.7% to 82.7% and 14.3% to 84.3%, with the 27B model outperforming frontier models. On Verina, both models reached 90.5% and beat VeriSpecGen-30B-A3B. Weights, 3,037 problems, and the 300-problem AuXSpec-Test set are released.

Unconfirmed: Benchmark gains and the claim of beating frontier models are the authors' reported results.

Key facts
  • Verina pass@1 rose from 7.0% to 90.5% and 21.9% to 90.5%.
  • Prior open-source leader VeriSpecGen-30B-A3B scored 47.6% pass@1 and 63.9% at pass@10.
  • AuXSpec-Test includes expert review and correctness proofs.
  • Models and data are on the eth-algopt Hugging Face collection.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Formal specifications define intended program behavior and underpin verification, but writing them in theorem provers such as Lean is slow and expertise-intensive, making specification a major bottleneck to scaling formally correct code.

Hugging Face daily papers

By Haocheng Wang, Weixuan Yuan, Florian Hübler · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.