LLM Agent环境中的审计行动结算
一项研究审计了LLM代理环境中五种结算政策,重点关注订单敏感性、有用进展和回放一致性。
一项研究审计了LLM代理环境中五种结算政策,重点关注订单敏感性、有用进展和回放一致性。
Five settlement policies are tested in 28,800 exhaustive permutation trials and 2,160 scripted multistep episodes.
Abstract: Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement contract and audit three distinct properties: order sensitivity, useful progress, and replay consistency. Five settlement policies are tested in 28,800 exhaustive permutation trials and 2,160 scripted multistep ep…