# Self-Spec Verifiable Code Generation

arXiv: https://arxiv.org/abs/2609.39568 · HTML: https://mlsanity.com/paper/2609.39568/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2306.15626/) (2023)
- [MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics](https://mlsanity.com/paper/2109.00110/) (2021)
- [ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics](https://mlsanity.com/paper/2302.12433/) (2023)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [Planning In Natural Language Improves LLM Search For Code Generation](https://mlsanity.com/paper/2409.03733/) (2024)
- [Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM](https://mlsanity.com/paper/2402.00097/) (2024)
- [nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models](https://mlsanity.com/paper/2303.04864/) (2023)
- [Towards AI-Assisted Synthesis of Verified Dafny Methods](https://mlsanity.com/paper/2402.00247/) (2024)
- [Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification](https://mlsanity.com/paper/2404.00762/) (2024)
- [Verus: Verifying Rust Programs using Linear Ghost Types (extended version)](https://mlsanity.com/paper/2303.05491/) (2023)
- [SpecGen: Automated Generation of Formal Program Specifications via Large Language Models](https://mlsanity.com/paper/2401.08807/) (2024)
- [PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation](https://mlsanity.com/paper/2405.02580/) (2024)
- [AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing](https://mlsanity.com/paper/2409.10737/) (2024)
- [AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement](https://mlsanity.com/paper/2412.06176/) (2024)
- [VERINA: Benchmarking Verifiable Code Generation](https://mlsanity.com/paper/2505.23135/) (2025)
- [CLEVER: A Curated Benchmark for Formally Verified Code Generation](https://mlsanity.com/paper/2505.13938/) (2025)
- [Proving the Coding Interview: A Benchmark for Formally Verified Code Generation](https://mlsanity.com/paper/2502.05714/) (2025)
- [Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference](https://mlsanity.com/paper/2503.04779/) (2025)
- [AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms](https://mlsanity.com/paper/2602.09464/) (2026)
- [ClassInvGen: Class Invariant Synthesis using Large Language Models](https://mlsanity.com/paper/2502.18917/) (2025)
- [Supporting Software Formal Verification with Large Language Models: An Experimental Study](https://mlsanity.com/paper/2507.04857/) (2025)
- [WybeCoder: Verified Imperative Code Generation](https://mlsanity.com/paper/2603.29088/) (2026)
- [Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs](https://mlsanity.com/paper/2507.03659/) (2025)
- [MINIF2F-DAFNY: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification](https://mlsanity.com/paper/2512.10187/) (2025)

## Abstract (arXiv)

Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently, researchers have proposed several benchmarks to evaluate the capabilities of LLMs in generating formally verifiable code, where LLMs need to formulate formal specifications, generate the corresponding code, and verify its correctness. However, existing benchmarks have two key limitations: (I) They primarily evaluate specification and code generation stage-wise, with code generation typically conditioned on an oracle specification. This setup overlooks whether strong stage-wise performance translates into end-to-end success. (II)They mainly focus on a single proof-oriented language and mathematically structured tasks, offering limited coverage of tasks common in software development. In this paper, we introduce VeriCodeBench, a benchmark for self-spec verifiable code generation, where the LLM relies solely on its own generated specification and code throughout the entire process. VeriCodeBench contains 400 language-native problems across C, Java, Rust, and Python, covering practical concerns in software development. We evaluate specification coverage, code validity, and joint problem-level success. We further introduce CodeNova to enhance the capabilities of LLMs in self-spec verifiable code generation. CodeNova makes requirements explicit through constraint-guided specification and uses verifier feedback to guide targeted implementation repairs. Experimental results reveal that self-generated specifications remain a major bottleneck, while providing more sophisticated specifications may not necessarily lead to higher verification success rates. CodeNova substantially improves performance across all evaluation metrics, enabling Claude Sonnet 5 to achieve the strongest results under the self-spec protocol.