AgentDAO: Synthesis of Proposal Transactions Via Abstract DAO Semantics

2025-03-13

AI Summary

High proposal thresholds in DAO governance—stemming from the manual authoring of on-chain transaction code—impede non-technical participants. To address this, we propose DAOLang, a domain-specific language (DSL) for DAO governance, coupled with a Label-Centric Retrieval algorithm that enables semantic-aware, lightweight abstraction from natural-language proposals to executable on-chain transactions. Our approach integrates multi-agent coordination with the GPT-4o large language model (LLM), achieving high generation fidelity while significantly reducing LLM token consumption. Evaluated in real-world DAO settings, the system successfully generates complex, production-grade proposals—including budget allocations, smart contract upgrades, and membership admissions—demonstrating an end-to-end automated governance pipeline that is low-overhead, highly reliable, and broadly accessible.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

While the trend of decentralized governance is obvious (cryptocurrencies and blockchains are widely adopted by multiple sovereign countries), initiating governance proposals within Decentralized Autonomous Organizations (DAOs) is still challenging, i.e., it requires providing a low-level transaction payload, therefore posing significant barriers to broad community participation. To address these challenges, we propose a multi-agent system powered by Large Language Models with a novel Label-Centric Retrieval algorithm to automate the translation from natural language inputs into executable proposal transactions. The system incorporates DAOLang, a Domain-Specific Language to simplify the specification of various governance proposals. The key optimization achieved by DAOLang is a semantic-aware abstraction of user input that reliably secures proposal generation with a low level of token demand. A preliminary evaluation on real-world applications reflects the potential of DAOLang in terms of generating complicated types of proposals with existing foundation models, e.g. GPT-4o.

Problem

• Automates translation of natural language into DAO proposal transactions.
• Simplifies governance proposal specification using DAOLang language.
• Reduces token demand for secure proposal generation in DAOs.

Innovation

• Multi-agent system with Large Language Models
• Label-Centric Retrieval algorithm for automation
• DAOLang for semantic-aware proposal abstraction