Vibe-Trading:面向金融交易的 Agent 原生框架
Vibe-Trading: Towards Agent-Native Trading
做量化或交易 Agent 的开发者可以看看这个开源框架,它把回测、模拟盘、多智能体协作到实盘执行整合在一个工作区里。和普通 Agent 框架最大的不同是强制给每个结论打上数据快照和时间戳,还用权限门隔开研究和实盘,能避免拿着过期信号下单一类的坑。
研究团队在 arXiv 发布 Vibe-Trading 框架,定位为 Agent 原生(agent-native)的金融交易系统,覆盖市场研究、金融数据、策略生成、回测、组合分析、模拟盘交易、多智能体协作与可选券商实盘执行八个环节。针对现有 AI Agent 依赖静态工作流、难以在市场环境持续变化时保持可靠状态的问题,该框架让每个结果都绑定其数据来源、时间快照、配置与产生该结果的运行记录,确保结论与正确的时点和执行上下文相关联。
架构上的核心机制有三点:共享证据锚定(evidence grounding)支持结果验证,带版本的研究记录支持可复现的后续研究,显式权限门(authority gate)将策略研究与实盘执行分离——只有获得明确授权,研究结果才能转化为交易动作。
金融交易对状态一致性要求远高于一般 Agent 场景:价格、新闻、市场状况、持仓与可用资金都在连续变化,脱离时点与数据快照的结论没有价值。这一框架为构建结果可追溯、可复现、且仅在显式授权下执行的交易 Agent 提供了工程基础。
Vibe-Trading: Towards Agent-Native Trading
Existing AI agents can retrieve information, call tools, run experiments, and produce multi-step outputs. Yet most are built around relatively static workflows and struggle to preserve reliable state as the environment changes. Financial trading makes this limitation especially consequential: prices, news, market conditions, portfolio positions, and available capital evolve continuously. A result is useful only when it remains tied to the correct time, data snapshot, and execution context. We present Vibe-Trading, a comprehensive agent-native trading framework and all-in-one workspace for building, evaluating, and evolving agents for financial trading. It unifies market research, financial data, strategy generation, backtesting, portfolio analysis, paper trading, multi-agent collaboration, and optional broker execution. Its central contribution is an architecture that keeps results, evidence, research history, and trading authority connected throughout the research-to-action process. Each result retains its source, temporal scope, configuration, and producing run. Shared evidence grounding enables verification, versioned research records support reproducible continuation, and an explicit authority gate separates strategy research from live execution. Together, these designs provide a practical foundation for trading agents whose results can be traced, reproduced, and acted on only under explicit authority.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Vibe-Trading, agents, quantitative trading, backtesting.
Source attribution: curated from arXiv cs.AI (@Haozhe Wu, Zhonghang Li, Chao Huang).