TradeGauntlet:用限价簿模拟器测试自动交易智能体的合规控制
TradeGauntlet: Evaluating Compliance Controls for Autonomous Trading Agents
做交易类智能体的人值得看这个:它不只是跑分,而是把警报、拦截、执行成本拆开验证。结论很反直觉——零警报不等于合规,搜索方法还能找到绕过规则的拆单方案。做过自动化交易或想给智能体上风控的团队都能直接参考。
研究团队发布了 TradeGauntlet,一个可重放的限价订单簿模拟器,用于拆分评估自动交易智能体的检测、预防与执行成本三层控制。在 1,680 场模拟会话中,Claude Haiku 5.5 与 Sonnet 5.5 触发的所有行为警报均为自成交(self-match);订单门控通过拒绝自交叉订单消除了这些警报,而聚合门控条件使 Sonnet 的双边成交减少约 15%。
实验进一步区分了"零警报"与真正合规的差距:脚本探针与两种搜索方法发现能绕过现有行为规则的拆单调度;一个学习型基线能捕获全部 2,400 个搜索生成的样本,但也会误报大型做市商 15% 的会话。聚合上限对操纵收益的削减并不均匀,当只有近触深度影响价格时削减幅度变小。
市场假设显著影响结论:拟合五只 Nasdaq 股票的响应模型与单独的 ABIDES 实验暴露了估计值对市场假设的依赖。对抗性提示方面,Sonnet 在全部 240 轮中均拒绝配合,未产生可评估的候选策略。论文强调这些实验不构成法律合规证明或真实市场检测精度的结论。
TradeGauntlet: Evaluating Compliance Controls for Autonomous Trading Agents
Autonomous trading agents need controls that prevent problematic orders without making legitimate tasks impractical. We study this aspect of agentic compliance with TradeGauntlet, a replayable limit-order-book simulator that separates detection, prevention, and execution cost. In 1,680 simulated sessions with Claude Haiku 5.5 and Sonnet 5.5, all conduct alerts were self-matches. Gates eliminated those alerts by rejecting self-crossing orders, while the aggregate-gate condition reduced Sonnet's two-sided fills by about 15%. A conduct reminder reduced Sonnet's alert rate but reduced Haiku's fills without a detectable alert benefit. These results show why zero alerts alone do not establish an agent's compliance. Scripted probes and two search methods test weaknesses beyond those observed in the LLM runs. The searches find split-order schedules that evade the implemented conduct rules; a learned baseline catches all 2,400 tested searched episodes but also flags 15% of a large maker's sessions. Aggregate caps reduce the response-dependent gain unevenly, with smaller reductions when only near-touch depth affects prices. A response fitted to five Nasdaq stocks and a separate ABIDES experiment expose the dependence of these estimates on market assumptions. A distinct adversarial prompt elicited refusals from Sonnet in all 240 rounds, yielding no candidate strategies to evaluate. TradeGauntlet provides reproducible tests of controls around trading agents; the experiments do not establish legal compliance or real-market detection accuracy.
本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「各国 AI 监管法案、合规治理与主权算力政策」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:TradeGauntlet、Claude、智能体、交易合规,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Sandip Nandi, Aishwarya Bose, Apurba Bose, Soovadeep Bakshi),经 AITOP 多维评分管线结构化提炼。