paper-with-me

Papers

AutoICE: Automatically Synthesizing Verifiable C Code via LLM-driven Evolution

2025-12-08 · Weilin Luo, Xueyi Liang, Haotian Deng, Yanan Liu, Hai Wan arxiv

Automatically synthesizing verifiable code from natural language requirements ensures software correctness and reliability while significantly lowering the barrier to adopting the techniques of formal methods. With the rise of large language models (LLMs), long-standing efforts at autoformalization have gained new momentum. However, existing approaches suffer from severe syntactic and semantic errors due to the scarcity of domain-specific pre-training corpora and often fail to formalize implicit knowledge effectively. In this paper, we propose AutoICE, an LLM-driven evolutionary search for synthesizing verifiable C code. It introduces the diverse individual initialization and the collaborative crossover to enable diverse iterative updates, thereby mitigating error propagation inherent in single-agent iterations. Besides, it employs the self-reflective mutation to facilitate the discovery of implicit knowledge. Evaluation results demonstrate the effectiveness of AutoICE: it successfully verifies $90.36$\% of code, outperforming the state-of-the-art (SOTA) approach. Besides, on a developer-friendly dataset variant, AutoICE achieves a $88.33$\% verification success rate, significantly surpassing the $65$\% success rate of the SOTA approach.

📄 PDF Abstract BibTeX arXiv:2512.07501

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner

2025-06-10 · Lei Zhang, Jiaxi Yang, Min Yang, Jian Yang 외

We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incr…

test driven development

PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data

2025-08-21 · Kai Xiong, Yanwei Huang, Rongjunchen Zhang, Kun Chen 외 arxiv

High-quality mathematical and logical datasets with verifiable answers are essential for strengthening the reasoning capabilities of large language models (LLMs). While recent data augmentation techniques have facilitate…

Data Augmentation

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

2026-04-30 · Hanane Nour Moussa, Yifei Li, Zhuoyang Li, Yankai Yang 외 arxiv

Despite recent progress in language models and agents for scientific data-driven discovery, advancing their capabilities is held back by the absence of verifiable environments representing real-world scientific tasks. To…

CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning

2026-01-27 · Van-Quang Nguyen, Takayuki Okatani arxiv

Existing datasets for multimodal table understanding, such as MMTab, primarily provide short factual answers without explicit multi-step reasoning supervision. Models trained on these datasets often generate brief respon…

Question AnsweringFact Verification

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

2026-01-30 · Ximing Lu, David Acuna, Jaehun Jung, Jian Hu 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked by limited existing verifiable data, wher…

Reinforcement Learning