AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes
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
多层验证框架确保自校正 LLM 交易代理的安全性。
- 核心方法
- AllPath 采用三层验证机制：编码层验证不可变的规则，如风险限制；代理层在固定范围内自我验证，每晚回溯并提出策略修订；人工层进行最终检查和授权。
- 适合谁读
- 研究者、工程师、产品
- 要解决的问题
- 论文探讨了如何在真实交易环境中，通过多层验证机制确保自校正 LLM 交易代理的安全性和可靠性。
- 关键实验
- 使用真实股票市场的模拟账户进行部署，展示了如何通过多层验证机制捕捉不同类型的失败。
- 主要贡献
- 提出了一种新颖的多层验证框架，能够在真实交易环境中提高 LLM 交易代理的安全性和自适应能力。
- 意义与局限
- 该系统为 LLM 交易代理在真实市场中的应用提供了安全框架，但其效果和通用性仍需进一步验证。