# GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts arXiv: https://arxiv.org/abs/2507.15761 ยท HTML: https://mlsanity.com/paper/2507.15761/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. - Builds on 31 of its 60 references that are in the map. - First posted on arXiv 21 Jul 2025. ## Placed in - LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/) ## Builds on (most cited first, 30 of 31) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023) - [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023) - [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020) - [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021) - [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024) - [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023) - [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022) - [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023) - [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023) - [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023) - [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023) - [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023) - [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023) - [Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://mlsanity.com/paper/2310.19923/) (2023) - [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019) - [TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage](https://mlsanity.com/paper/2308.03427/) (2023) - [Simulating Public Administration Crisis: A Novel Generative Agent-Based Simulation System to Lower Technology Barriers in Social Science Research](https://mlsanity.com/paper/2311.06957/) (2023) - [An Overview on Smart Contracts: Challenges, Advances and Platforms](https://mlsanity.com/paper/1912.10370/) (2019) - [Under-Optimized Smart Contracts Devour Your Money](https://mlsanity.com/paper/1703.03994/) (2017) - [GASOL: Gas Analysis and Optimization for Ethereum Smart Contracts](https://mlsanity.com/paper/1912.11929/) (2019) - [Smart Contracts in the Real World: A Statistical Exploration of External Data Dependencies](https://mlsanity.com/paper/2406.13253/) (2024) - [How to Save My Gas Fees: Understanding and Detecting Real-world Gas Issues in Solidity Programs](https://mlsanity.com/paper/2403.02661/) (2024) - [An Adaptive Gas Cost Mechanism for Ethereum to Defend Against Under-Priced DoS Attacks](https://mlsanity.com/paper/1712.06438/) (2017) - [Profiling Gas Consumption in Solidity Smart Contracts](https://mlsanity.com/paper/2008.05449/) (2020) ## Built on by (most cited first, 5 of 5) - [BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Web](https://mlsanity.com/paper/2508.13787/) (2025) - [Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents](https://mlsanity.com/paper/2510.17491/) (2025) - [What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media](https://mlsanity.com/paper/2606.06784/) (2026) - [TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding](https://mlsanity.com/paper/2512.06933/) (2025) - [TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation](https://mlsanity.com/paper/2608.27127/) (2026) ## Abstract (arXiv) 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.