TwinCheck：针对状态工具代理的循证负孪生验证

arXiv:2609.26911v1 公告类型：新 摘要：单个本地合理的工具调用可能会破坏原本成功的代理轨迹。仅凭怀疑并不能证明干预是合理的，因为更换本身可能会引入本应防止的故障验证。我们引入了 TwinCheck，这是一种推理时验证策略，仅当跟踪满足与跟踪局部故障假设相关的证据条件时才考虑替换。 It constructs a trace-grounded counterfactual alternative, a negative twin, and replaces the agent's proposal only if the twin passes structural checks and the pairwise verifier prefers it in both candidate orders. For paired evaluation, exact replay holds the agent's parsed responses and actions fixed until the first accepted replacement, separating intervention effects from resampling. In the primary analysis of 159 multi-turn BFCL V4 tasks with complete exact-replay pairs, the complete policy raises task success for GPT-5.6 Sol from 45.3% to 58.5% (95% task-bootstrap CI [8.2, 18.8]), with no observed success-to-failure regressions. Together, these findings recast execution-boundary repair as a constrained comparison, making the counterfactual action itself the object of verification.