你的智能体说“是”：解读超越单笔交易的对抗性市场行为
Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions
- Ohio State University（俄亥俄州立大学）
- Rutgers University（罗格斯大学）
- Linux Foundation（Linux基金会）
- University of Manchester（曼彻斯特大学）
- Columbia University（哥伦比亚大学）
- McGill University（麦吉尔大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究在虚拟交易所中通过对抗性语言模型智能体揭示交易局部控制无法捕捉跨消息、智能体和时间的分布式市场行为，提出应结合通信、授权与演化状态进行智能体行为评估。
AI中文摘要：
交易局部控制只能回答单个金融请求是否可以执行，但市场行为可能分布在消息、智能体、资产和时间之中。我们在一个由十个角色条件化语言模型智能体组成的虚拟交易所中研究这一解释差距。这些智能体在规范性对抗角色下进行通信、交易参考资产和期货、发行代币并管理集中流动性池。我们分析了跨越两条时间盲化的小时级回放路径的八条72周期轨迹，并启用或禁用了运行方钱包策略。保留的工件将生成的出站消息、策略事件、余额、持仓和周期末市场状态关联起来。一个焦点重建展示了一个在私人协调、公开声明、追随者持仓、反复延迟退出以及后来与代币余额变化一致的非阻塞请求中实现的“发行—推广—退出”场景。在启用策略的运行中，门控选择性地扣留直接请求；大多数按策略分类的候选被标记而非阻止，而周围的交互可以继续。重复运行还表明，即使归一化得分变化排名不一致，类别级和轨迹内关系也可能重复出现。这些发现促使智能体行为评估将通信、授权和演化状态联系起来，而不是将单个交易判定视为完整的安全判断。
英文摘要：
Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets, and time. We study this interpretation gap in a virtual exchange populated by ten role-conditioned language-model agents. The agents communicate, trade reference assets and futures, launch tokens, and manage concentrated-liquidity pools under prescriptive adversarial roles. We analyze eight 72-cycle trajectories across two time-blinded hourly replay paths, with a runner-side wallet policy enabled or disabled. The retained artifacts connect generated outgoing messages, policy events, balances, positions, and cycle-end market state. A focal reconstruction shows a launch--promotion--exit scenario realized across private coordination, public claims, follower positioning, repeatedly withheld exits, and a later non-blocking request aligned with a token balance change. Across policy-enabled runs, the gate withholds direct requests selectively; most policy-categorized candidates are flagged rather than blocked, while the surrounding interaction can continue. Repeated runs also show that category-level and within-trajectory relations can recur even when normalized score-change rankings do not. These findings motivate agent-behavior evaluation that links communication, authorization, and evolving state instead of treating individual transaction verdicts as complete safety judgments.
