paper-with-me

Papers

AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement

2024-12-09 · Pranjal Aggarwal, Bryan Parno, Sean Welleck

Automated code generation with large language models has gained significant traction, but there remains no guarantee on the correctness of generated code. We aim to use formal verification to provide mathematical guarantees that the generated code is correct. However, generating formally verified code with LLMs is hindered by the scarcity of training data and the complexity of formal proofs. To tackle this challenge, we introduce AlphaVerus, a self-improving framework that bootstraps formally verified code generation by iteratively translating programs from a higher-resource language and leveraging feedback from a verifier. AlphaVerus operates in three phases: exploration of candidate translations, Treefinement -- a novel tree search algorithm for program refinement using verifier feedback, and filtering misaligned specifications and programs to prevent reward hacking. Through this iterative process, AlphaVerus enables a LLaMA-3.1-70B model to generate verified code without human intervention or model finetuning. AlphaVerus shows an ability to generate formally verified solutions for HumanEval and MBPP, laying the groundwork for truly trustworthy code-generation agents.

📄 PDF Abstract BibTeX arXiv:2412.06176

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationHumanEvalmbpp

Similar Papers 제목 키워드 기반

A benchmark for vericoding: formally verified program synthesis

2025-09-26 · Sergiu Bursuc, Theodore Ehrenborg, Shaowei Lin, Lacramioara Astefanoaei 외 arxiv

We present and test the largest benchmark for vericoding, LLM-generation of formally verified code from formal specifications - in contrast to vibe coding, which generates potentially buggy code from a natural language d…

Program Synthesis

Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning

2025-09-07 · Manvi Jha, Jiaxin Wan, Deming Chen arxiv

Large Language Models (LLMs) have demonstrated impressive capabilities in automated code generation but frequently produce code that fails formal verification, an essential requirement for hardware and safety-critical do…

Reinforcement LearningCode Generation

Proving the Coding Interview: A Benchmark for Formally Verified Code Generation

2025-02-08 · Quinn Dougherty, Ronak Mehta

We introduce the Formally Verified Automated Programming Progress Standards, or FVAPPS, a benchmark of 4715 samples for writing programs and proving their correctness, the largest formal verification benchmark, including…

Automated Theorem ProvingCode GenerationProgram Synthesis

CLEVER: A Curated Benchmark for Formally Verified Code Generation

2025-05-20 · Amitayush Thakur, Jasper Lee, George Tsoukalas, Meghana Sistla 외

We introduce ${\rm C{\small LEVER}}$, a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of generating a specification that matches a …

Code GenerationProgram Synthesis

Vero: Can AI Agents Build Formally Verified Software Repositories?

2026-08-13 · Zhe Ye, Hantao Lou, Yuechun Sun, Peiyang Song 외 arxiv

AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked pr…

Code Generation