Author: 0XNATALIE
Since the second half of this year, the topic of AI Agent has been continuously rising in popularity. Initially, the AI chatbot terminal of truths gained widespread attention for its humorous posts and replies (similar to "Robert" on Weibo) on X, and received a $50,000 grant from a16z founder Marc Andreessen. Inspired by the content it released, someone created the GOAT token, which surged over 10,000% in just 24 hours. The topic of AI Agent then caught the attention of the Web3 community. Subsequently, the first decentralized AI trading fund ai16z based on Solana was launched, introducing the AI Agent development framework Eliza, and triggering a debate over capitalization of tokens. However, the community still lacks a clear understanding of the concept of AI Agent: what is the core of AI Agent? How is it different from Telegram trading bots?
Working Principle: Perception, Reasoning, and Autonomous Decision-making
AI Agent is an intelligent agent system based on large language models (LLMs), which can perceive the environment, make reasoning decisions, and complete complex tasks by calling tools or executing operations. The workflow is: Perception module (obtaining input) → LLM (understanding, reasoning, and planning) → Tool invocation (task execution) → Feedback and optimization (verification and adjustment).
Specifically, the AI Agent first obtains data (such as text, audio, images, etc.) from the external environment through the perception module, and converts it into structured information that can be processed. The LLM, as the core component, provides powerful natural language understanding and generation capabilities, acting as the "brain" of the system. Based on the input data and existing knowledge, the LLM performs logical reasoning, generating possible solutions or formulating action plans. Subsequently, the AI Agent completes specific tasks by calling external tools, plugins, or APIs, and verifies and adjusts the results based on feedback, forming a closed-loop optimization.
In the Web3 application scenario, how does the AI Agent differ from Telegram trading bots or automation scripts? Taking arbitrage as an example, the user wants to perform arbitrage transactions with a profit greater than 1%. In the Telegram trading bot that supports arbitrage, the user sets the trading strategy with a profit greater than 1%, and the Bot will start executing. However, when the market fluctuates frequently and arbitrage opportunities keep changing, these Bots lack the ability to assess risks, and will execute arbitrage as long as the profit exceeds 1%. In contrast, the AI Agent can automatically adjust its strategy. For example, when a trade's profit exceeds 1%, but through data analysis it assesses the risk as too high and the market may suddenly change, causing a loss, it will decide not to execute that arbitrage.
Therefore, the AI Agent has self-adaptability, and its core advantage lies in its ability to self-learn and make autonomous decisions. Through interaction with the environment (such as the market, user behavior, etc.), it adjusts its behavioral strategies based on feedback signals, continuously improving the execution of tasks. It can also make decisions in real-time based on external data, and continuously optimize its decision-making strategies through reinforcement learning.
Doesn't this sound a bit like a solver under the intent framework? The AI Agent itself is also a product of the intent framework, but the biggest difference from the solver under the intent framework is that the solver relies on precise algorithms and has mathematical rigor, while the AI Agent's decision-making depends on data training, often requiring constant trial and error in the training process to approach the optimal solution.
Mainstream AI Agent Frameworks
The AI Agent framework is the infrastructure for creating and managing intelligent agents. Currently, the popular frameworks in Web3 include Eliza from ai16z, ZerePy from zerebro, and GAME from Virtuals.
Eliza is a multi-functional AI Agent framework built with TypeScript, supporting operation on multiple platforms (such as Discord, Twitter, Telegram, etc.), and through complex memory management, it can remember previous conversations and context, maintaining stable and consistent personality traits and knowledge responses. Eliza adopts a Retrieval Augmented Generation (RAG) system, which can access external databases or resources to generate more accurate responses. In addition, Eliza integrates the TEE plugin, allowing deployment in the TEE to ensure data security and privacy.
GAME is a framework that empowers and drives AI Agents to make autonomous decisions and actions. Developers can customize the agent's behavior and expand its functionality according to their own needs, and provide customized operations (such as social media posting, replying, etc.). The different functions in the framework, such as the agent's environmental location and tasks, are divided into multiple modules, making it convenient for developers to configure and manage. The GAME framework divides the AI Agent's decision-making process into two levels: High-Level Planning (HLP) and Low-Level Planning (LLP), responsible for different levels of tasks and decisions. High-level planning is responsible for setting the agent's overall goals and task planning, formulating decisions based on goals, personality, background information, and environmental status, and determining the priority of tasks. Low-level planning focuses on the execution level, translating the high-level planning decisions into specific operational steps, and selecting appropriate functions and methods of operation.
ZerePy is an open-source Python framework for deploying AI Agents on X. The framework integrates the LLMs provided by OpenAI and Anthropic, allowing developers to build and manage social media agents and automate operations such as posting tweets, replying to tweets, and liking. Each task can be assigned different weights based on its importance. ZerePy provides a concise command-line interface (CLI) for developers to quickly start and manage agents. At the same time, the framework also provides a Replit (an online code editing and execution platform) template, allowing developers to quickly get started with ZerePy without complex local environment configuration.
Why Does AI Agent Face FUD?
AI Agent seems intelligent and can reduce the entry barrier and improve the user experience, so why does the community have FUD? The reason is that the AI Agent is essentially still just a tool, and it cannot currently complete the entire workflow. It can only improve efficiency and save time at certain nodes. Moreover, in the current development stage, the role of the AI Agent is mainly focused on helping users issue MeMes and operate social media accounts. The community jokingly says "assets belong to Dev, liabilities belong to AI".
However, just this week, aiPool, as the AI Agent for token pre-sale, was released, utilizing TEE technology to achieve trustlessness. The wallet private key of this AI Agent is dynamically generated in the TEE environment, ensuring security. Users can send funds (such as SOL) to the wallet controlled by the AI Agent, and the AI Agent will then create tokens according to the set rules and launch a liquidity pool on the DEX, while distributing tokens to qualified investors. The entire process does not rely on any third-party intermediaries and is completed autonomously by the AI Agent in the TEE environment, avoiding the common rug pull risk in DeFi. It can be seen that the AI Agent is gradually developing. I believe that the AI Agent can help users reduce thresholds and improve experiences, even if it only simplifies part of the asset issuance process, it is meaningful. But from the macro perspective of Web3, the AI Agent, as an off-chain product, is currently only playing an auxiliary role to smart contracts, so there is no need to overhype its capabilities. Due to the lack of significant wealth effect narratives other than MeMes in the second half of this year, the hype around AI Agent is centered on MeMes, which is normal. Relying solely on MeMes cannot sustain long-term value, so if the AI Agent can bring more innovative gameplay to the transaction process and provide practical application value, it may develop into a common infrastructure tool.
