Apr 2026· Proceedings of the 2026 IEEE/ACM 48th International Conference on Software Engineering· 1 citation· 69 references
Computer Science
TL;DR
This work systematically analyzed the grammatical and semantic features that lead to excessive Gas consumption and proposes RAGas, a three-stage retrieval enhancement generation framework that utilizes large language models to locate and automatically fix Gas inefficiency issues.
Abstract
Ethereum has gradually become an infrastructure in key areas such as finance, healthcare, and supply chain. When its smart contracts are executed, Gas fees increase with the growth of computational complexity. Therefore, reducing code with high Gas overhead while maintaining functional equivalence is of great significance to deployment costs. Currently available tools rely on fixed rule sets and cannot autonomously adapt to the dynamically evolving patterns of Gas consumption. To this end, we systematically analyzed the grammatical and semantic features that lead to excessive Gas consumption and constructed 12 fine-grained High Gas Consumption (HGC) patterns and knowledge bases covering 6 major categories. Based on this, we propose RAGas, a three-stage retrieval enhancement generation framework that utilizes large language models to locate and automatically fix Gas inefficiency issues. The experimental results show that RAGas can reduce Gas usage by up to 11.2% in real world deployed contracts.
LLMs-RAG-CFA, a unified framework that combines large language models with retrieval-augmented generation (RAG) to deliver real-time, reliable, cost-efficient, and privacy-preserving CFA, offers a scalable, practical pathway for real-time carbon emission monitoring and supports improved sustainability practices.
H.-J. Wang, M.-R. Zhang, Z. Chen et al.· Journal of Environmental Inf...· 0 citations
CompVault, an Enhanced Retrieval-Augmented Generation (ERAG)-based Artificial Intelligence Compliance Monitoring and Report Generation System for intelligent regulatory compliance assessment, and results indicate that the ERAG-based framework can be used as an efficient, scalable, and explainable solution for regulator...
S. N., Sathyapriya P., V. M. et al.· Journal of Information Techn...· 0 citations
Many Internet of Things (IoT) services provide Representational State Transfer (REST) APIs, which require client developers to implement applications that conform to the corresponding API specifications. When client programs contain API misuse, developers debug them based on error responses. However, such responses are...
Shoei Inoue, Norihiro Yoshida, Erina Makihara et al.· 0 citations
In high-risk industrial settings, leveraging large language models (LLMs) for automated accident analysis and generating safety reports has emerged as an efficient workflow. However, this approach is fundamentally constrained by the models’ inherent knowledge limitations, frequently resulting in analyses that lack do...
Qi Cao, Chiyu Zhang, Junxiong Ning et al.· SPE Journal· 0 citations
Automated feature engineering with large language models (LLMs) can produce semantically meaningful features for tabular data, yet existing methods lack structured domain knowledge, rigorous verification, and explainable provenance. We propose KnowFeat, a knowledge-guided feature engineering framework that organizes do...
Chengsong You, Wangyue Li, Wei-Qiao Que et al.· 0 citations
A lightweight utility-guided orchestration framework that formulates agent control as a costaware sequential decision problem over a compact action space, intended as an inspectable control layer for practical LLM services rather than a universally dominant accuracy optimizer.
Bo-Yang Liu, Gongming Zhao, Hong-Liu Xu et al.· Fall Joint Computer Conferen...· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
