# SolAgent: A Specialized Multi-Agent Framework for Solidity Code Generation

arXiv: https://arxiv.org/abs/2601.23009 · HTML: https://mlsanity.com/paper/2601.23009/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 25 of 25)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction](https://mlsanity.com/paper/2209.11515/) (2022)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019)
- [GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis](https://mlsanity.com/paper/2308.03314/) (2023)
- [When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?](https://mlsanity.com/paper/2309.05520/) (2023)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention](https://mlsanity.com/paper/2407.20042/) (2024)
- [RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository](https://mlsanity.com/paper/2601.13943/) (2026)
- [Under-Optimized Smart Contracts Devour Your Money](https://mlsanity.com/paper/1703.03994/) (2017)
- [SmartInv: Multimodal Learning for Smart Contract Invariant Inference](https://mlsanity.com/paper/2411.09217/) (2024)
- [ContractTinker: LLM-Empowered Vulnerability Repair for Real-World Smart Contracts](https://mlsanity.com/paper/2409.09661/) (2024)
- [NumScout: Unveiling Numerical Defects in Smart Contracts using LLM-Pruning Symbolic Execution](https://mlsanity.com/paper/2503.10041/) (2025)
- [Unity is Strength: Enhancing Precision in Reentrancy Vulnerability Detection of Smart Contract Analysis Tools](https://mlsanity.com/paper/2402.09094/) (2024)
- [MulChain: Enabling Advanced Cross-Modal Queries in Hybrid-Storage Blockchains](https://mlsanity.com/paper/2502.18258/) (2025)
- [Input Reduction Enhanced LLM-based Program Repair](https://mlsanity.com/paper/2507.15251/) (2025)
- [Learning to Align Human Code Preferences](https://mlsanity.com/paper/2507.20109/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026)

## Abstract (arXiv)

Smart contracts are the backbone of the decentralized web, yet ensuring their functional correctness and security remains a critical challenge. While Large Language Models (LLMs) have shown promise in code generation, they often struggle with the rigorous requirements of smart contracts, frequently producing code that is buggy or vulnerable. To address this, we propose SolAgent, a novel tool-augmented multi-agent framework that mimics the workflow of human experts. SolAgent integrates a dual-loop refinement mechanism: an inner loop using the textitForge compiler to ensure functional correctness, and an outer loop leveraging the textitSlither static analyzer to eliminate security vulnerabilities. Additionally, the agent is equipped with file system capabilities to resolve complex project dependencies. Experiments on the SolEval+ Benchmark, a rigorous suite derived from high-quality real-world projects, demonstrate that SolAgent achieves a Pass@1 rate of up to 64.39%, significantly outperforming state-of-the-art LLMs (~25%), AI IDEs (e.g., GitHub Copilot), and existing agent frameworks. Moreover, it reduces security vulnerabilities by up to 39.77% compared to human-written baselines. Finally, we demonstrate that the high-quality trajectories generated by SolAgent can be used to distill smaller, open-source models, democratizing access to secure smart contract generation. We release our data and code at https://github.com/openpaperz/SolAgent.