arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.26662cs.AI
收藏

AllPath:面向已部署的、在人工管控与自主模式下运行的自修订LLM交易智能体的分层验证机制

AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes

Tian Zhang, Meng Li

AI总结:

本研究提出AllPath分层验证架构,针对实盘部署的自修订LLM交易智能体,对比人工管控与自主模式的验证策略,捕获回测无法观测的生产故障,为交易智能体部署提供验证方案。

摘要:

LLM交易智能体几乎仅在回测和自主基准测试工具中接受评估。在部署场景中,由于操作不可逆转,会产生不同的问题:谁来验证智能体的操作,以及每个验证者在结构上能捕获哪些故障?本文报告了AllPath,一款针对实盘模拟经纪账户部署的个人LLM交易智能体。该系统通过确定性规则引擎监控持仓,每晚复盘当日操作并提出交易策略修订方案。验证分为三层:代码验证不依赖判断的部分,确定性门控机制强制执行风险限额,并阻止任何未通过完整性检查的策略修订;智能体在固定范围内进行自验证,其夜间复盘设置了迭代上限,且无工具可执行操作;人工验证通过显示每个修订提案当前状态的审批界面完成。我们还在实盘系统上对比了智能体自修订的两种验证策略:两周半时间内所有自修订均为人工管控,随后五周内反思修订在相同代码门控后自动应用,而操作员的聊天通道全程保持人工管控。各层捕获了不同类型的故障:代码门控未拒绝任何提案,其作用是保持修订的一致性;人工拒绝了两项通过所有代码检查的提案,均因市场判断分歧,随后在8天的中位数滞后时间内移除了智能体自行添加的19条规则中的11条;最具启发性的生产事件(如策略被静默留存未监控)通过了所有门控,由操作员手动发现,每次修复均为修改界面使相关条件可见。我们贡献了分层架构、双模式账户以及生产事件分类法,这些均无法在回测中观测到。

英文摘要:

LLM trading agents are evaluated almost exclusively in backtests and autonomous benchmark harnesses. Deployment, where actions are irreversible, raises a different question: who verifies the agent's actions, and which failures can each verifier structurally catch? We report on AllPath, a personal LLM trading agent deployed against a live paper-brokerage account. The system watches positions through a deterministic rules engine, and each night it reviews its own day and proposes revisions to its own trading strategies. Verification is split across three layers. Code verifies what must not depend on judgment: deterministic gates enforce risk limits and block any strategy revision that fails an integrity check. The agent verifies itself within fixed bounds: its nightly review has an iteration cap and no tools that can act. A human verifies judgment, through approval screens that show the current state of each proposal. We also compared two verification policies for the agent's self-revisions on the live system: two and a half weeks with every self-revision human-gated, then five weeks with reflection revisions auto-applied behind the same code gates, while the operator's chat channel stayed human-gated throughout. Each layer caught a different kind of failure. The code gates rejected no proposal; their role was keeping revisions consistent. The human rejected two proposals that passed every code check, both over a disagreement about the market, and later removed 11 of the 19 rules the agent had added on its own, at a median lag of eight days. The most instructive production incidents, such as strategies silently left unmonitored, passed every gate; the operator found them by hand, and the fix each time was an interface change that makes the condition visible. We contribute the layered architecture, the two-regime account, and a production incident taxonomy, none observable in a backtest.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑