Newest papers

Better Specifications, Better Code: Fine-Tuning LLMs for Behavioral Contract Generation

Brhane Team, Tiantian Yang, Nikta Akbarpour, Simone Bartucci, Francesco Calimeri, Song Wang · 2026 · arXiv

DOI: 10.48550/arXiv.2610.25616 · open-access PDF

Japanese

大型言語モデル(LLMs)は強力なコード生成能力を示しているが、暗示的または曖昧な行動要件による機能的正確性と闘うことが多い。我々はCG2を紹介し、自然言語のタスクをインターフェイス、前条件、後条件、および不変性を指定する構造化された行動契約に翻訳する契約ガイドされたコード生成フレームワークを紹介します。

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models (LLMs) demonstrate strong code-generation capabilities but often struggle with functional correctness due to implicit or ambiguous behavioral requirements. We present CG2, a contract-guided code generation framework that translates natural-language tasks into structured behavioral contracts specifying interfaces, preconditions, postconditions, and invariants. CG2 fine-tunes an LLM to generate these contracts and introduces an iterative semantic validation and repair process to identify and correct incomplete, inconsistent, or incorrect specifications before guiding an unc

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange