Tian Zhang, Meng Li · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26662 · open-access PDF
LLM交易代理几乎完全在后测试和自主基准工具中进行评估。部署,其中行动是不可逆转的,提出了不同的问题:谁验证了代理人的行为,并且每个验证器可以结构性地捕捉哪些失败?我们在AllPath上报告,一个个人LLM交易代理部署在活纸经纪账户上。系统通过确定性规则引擎监控位置,每晚它都会审查自己的日子,并提出对自己的交易策略的修订。
Machine translation (Meta M2M100); the English original follows.
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 depen
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26662, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange