GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts

TL;DR

GasAgent is a multi-agent system that automates smart contract Gas optimization by discovering, validating, and applying Gas-saving patterns, significantly improving efficiency and compatibility with existing tools.

Contribution

It introduces the first multi-agent framework for automated Gas optimization that combines pattern compatibility with new pattern discovery and validation.

Findings

Optimized 82 real-world contracts with 9.97% average Gas savings.

Achieved 79.8% optimization rate on LLM-generated contracts with up to 13.93% savings.

Validated compatibility with existing tools and effectiveness of each module.

Abstract

Smart contracts are trustworthy, immutable, and automatically executed programs on the blockchain. Their execution requires the Gas mechanism to ensure efficiency and fairness. However, due to non-optimal coding practices, many contracts contain Gas waste patterns that need to be optimized. Existing solutions mostly rely on manual discovery, which is inefficient, costly to maintain, and difficult to scale. Recent research uses large language models (LLMs) to explore new Gas waste patterns. However, it struggles to remain compatible with existing patterns, often produces redundant patterns, and requires manual validation/rewriting. To address this gap, we present GasAgent, the first multi-agent system for smart contract Gas optimization that combines compatibility with existing patterns and automated discovery/validation of new patterns, enabling end-to-end optimization. GasAgent consists of four specialized agents, Seeker, Innovator, Executor, and Manager, that collaborate in a closed loop to identify, validate, and apply Gas-saving improvements. Experiments on 100 verified real-world contracts demonstrate that GasAgent successfully optimizes 82 contracts, achieving an average deployment Gas savings of 9.97%. In addition, our evaluation confirms its compatibility with existing tools and validates the effectiveness of each module through ablation studies. To assess broader usability, we further evaluate 500 contracts generated by five representative LLMs across 10 categories and find that GasAgent optimizes 79.8% of them, with deployment Gas savings ranging from 4.79% to 13.93%, showing its usability as the optimization layer for LLM-assisted smart contract development.