关于 Web3 AI Agent 落地场景方向的若干思考

链捕手Published on 2025-04-29Last updated on 2025-04-29

作者:Haotian

 

进一步思考了下关于 web3 AI Agent 落地场景方向,提炼若干前瞻思考,如下:

1)web3 AI Agent 最原生的应用功能可能并非「交易」。尽管 DeFi 交易类 Agent 一直被视为 Agent 落地 Crypto 的 Endgame 形态。但 AI 本身带有模糊性推理和幻觉过程,这与交易场景要求的精准性、低容错率天然相悖。

在我看来,短期 web3 AI Agent 的优势在「数据清洗」和「意图解析」层面,而非一下子就要落地到绝对精确度的资产交易执行层。比如:进行链上 + 链下适用性数据的清洗,构建有效信息图谱;又比如:展开链上用户交易行为的建模和风险偏好分析,定制 Smart Money 交易决策助理等等;

2)web3 AI Agent 对 A2A 这种 Agent 通信协议功能的需要可能大于 MCP。因为 MCP 调用相对都是成熟的功能性 API 接口,若前提有成熟的 Agent 应用生态,基于 MCP 可以完美解决数据孤岛问题,反之,若本身应用业态就不成熟,MCP 的标准化接口就缺乏用武之地。

相较之下,A2A 协议则可以创建一定 Agent 增量市场,会催生一批专业化分工的垂类 Agent 先行出现,如链上数据分析 Agent、智能合约审计 Agent、MEV 机会捕捉 Agent 等等。A2A 内置的 Agent 能力注册表和 P2P 消息传递网络等条件会促使各垂类 Agent 更好适配联动和复杂交互组合价值,若只停留在 MCP 协议层面,恐怕 web3 AI Agent 很难突破语言交互层面的局限。

3)web3 AI Agent 对 infra 构建的需求 > Application 落地。在 web2AI 语境下追求 Agent 的实用性价值自然优先级最高,但 web3 AI Agent 要想构建完整生态,必须填补严重缺失的底层基础设施,包括统一数据层、Oracle 层、意图执行层、去中心化共识层等 。

比起在应用层与 web2 硬刚(注定会吃亏),在 infra 层另辟蹊径,搭建具备 web3 差异化优势的 infra 才是正道。虽然在应用落地上相对 web2 AI 有所滞后,但为 A2A 运行构建去中心化共识网络,为 MCP 发挥效用构建统一的可交互操作标准等基础 infra,天然与区块链的原生特性高度契合,构建 infra 的迫切性并不比应用落地差多少。

4)从 Crypto Native 到 AI Native 的 build 思维定式转变,回望过去多少年的 Crypto 历史,仅一句「去中心化」框架的恪守就衍生出了丰富多样的赛道和创新潮,未来 AI +Crypto 领域,可能会围绕「AI 自主化」走更远的路。

无论是 Agentic 还是 Robotic,本质上都要追寻一套全新的以 AI 为中心的范式框架,比如,一套具有自我资金管理能力的 AI Agent 集群,一套可根据网络环境和反馈自升级的智能合约模版,一套基于社区贡献度动态调整优化的 DAO 治理框架等。归根结底,抽离简单的工具应用思维,让 AI 拥有自主演化系统,让 AI 驱动 AI 进步才是硬道理。

Trending Cryptos

Related Reads

Karpathy's Genius Strikes Again, Challenging RAG, Turning Your Notes into a Second Brain

Andrej Karpathy has proposed a revolutionary concept for managing personal knowledge: treating notes as immutable "source code" and using LLMs as "compilers" to build a structured, interlinked wiki. This approach fundamentally shifts the cognitive workflow away from the limitations of RAG (Retrieval-Augmented Generation), which merely retrieves and pieces together fragments, leading to contradictions and "digital mummies"—unused, decaying notes. The LLM-Wiki framework introduces a three-layer architecture: the **Raw Layer** for original, immutable notes; the **Schema Layer** defining rules for structuring knowledge; and the **Wiki Layer**, where the LLM continuously compiles and maintains a coherent, cross-referenced knowledge base. Key operations are **Ingest** (adding new material, which triggers updates across related pages), **Query** (asking the compiled wiki, with answers that can become new pages), and **Lint** (periodic AI audits to find contradictions, outdated claims, or gaps). This system automates the tedious maintenance—updating links, resolving conflicts, keeping summaries fresh—that has historically made large-scale personal knowledge management unsustainable. It realizes Vannevar Bush's 1945 "Memex" vision by finally solving the maintenance problem. Karpathy's proposal represents a third piece in human-AI collaboration, following "Vibe Coding" and "Agentic Engineering." It liberates human attention from organizational drudgery, refocusing it on what matters: deciding what to read and deriving meaning.

marsbit3m ago

Karpathy's Genius Strikes Again, Challenging RAG, Turning Your Notes into a Second Brain

marsbit3m ago

Claude Science Completes Two Years' Work in a Few Weeks, Is 10x Research Acceleration Really Here?

Claude Science, a new AI workbench from Anthropic, is being tested by scientists, reportedly accelerating specific research workflows by up to 10x. A neuro-scientist at the Allen Institute completed a lengthy literature review in weeks instead of nearly two years using the tool, which automates tasks like citation verification. The platform is an integrated environment for macOS and Linux, connecting to local or remote computing resources. It streamlines the fragmented research process—literature analysis, computation, visualization, and drafting—into a single, auditable workflow. A key feature is its emphasis on reproducibility: every chart generated includes the exact code, environment, and history used to create it. Claude Science uses a multi-agent system. A coordinator manages over 60 pre-configured skills for life sciences (genomics, proteomics, etc.) and can spawn specialized agents. A dedicated reviewer agent checks citations and calculations for accuracy, creating a form of internal AI peer review. The system operates with a human-in-the-loop, requiring user approval for major steps. Initial applications are in life sciences. Examples include target identification for biotech company Manifold Bio and germline variant analysis for glioma research at UCSF, completing analyses in roughly one-tenth the previous time. The approach contrasts with competitors: Google focuses on proprietary models like AlphaFold, while OpenAI is advancing models' scientific reasoning with benchmarks like GeneBench-Pro. Claude Science differentiates by automating and integrating the practical research pipeline, not just the model's intelligence, aiming to make AI-aided science more reproducible and integrated into daily lab work.

marsbit7m ago

Claude Science Completes Two Years' Work in a Few Weeks, Is 10x Research Acceleration Really Here?

marsbit7m ago

The Invisible Force in Bitcoin's Bear Market: Accelerating On-Chain Payments and Institutional Adoption

Amidst ongoing Bitcoin price volatility, the quiet acceleration of on-chain payments and tokenized trading holds significant importance for investors and policymakers, especially with legislation like the CLARITY Act on the horizon. Major traditional financial institutions adopting these technologies are driving crucial discussions on compliance, security, and transparency, which are vital for broader market adoption. Key developments are shaping this evolution. First, blockchain traceability is moving beyond a simple "public vs. private" debate. New frameworks aim to standardize how financial data from immutable ledgers is analyzed and interpreted, making it as crucial as standardized financial reporting for building institutional trust. Second, while traditional finance supports clear digital asset regulation, they emphasize that an asset's economic function should dictate its regulatory treatment, advocating for robust consumer protections over broad exemptions. Furthermore, the growth of on-chain deposits at regulated institutions signals a shift. Major banks are leveraging blockchain not to replace but to upgrade existing services—like deposits and cross-border settlements—with benefits like 24/7 operations and programmable treasury management. This trend focuses more on modernizing financial infrastructure than creating speculative assets. Despite market turbulence, these underlying advancements in on-chain infrastructure point toward a more robust foundation for the industry's future.

Foresight News54m ago

The Invisible Force in Bitcoin's Bear Market: Accelerating On-Chain Payments and Institutional Adoption

Foresight News54m ago

Trading

Spot

Hot Articles

Discussions

Welcome to the HTX Community. Here, you can stay informed about the latest platform developments and gain access to professional market insights. Users' opinions on the price of AI (AI) are presented below.

活动图片