בנק חוויות מבקר: הערכת ביטחון עצמית מתפתחת

תקציר מקורי באנגליתarXiv:2607.12397v2 Announce Type: replace Abstract: LLM agents operate in stateful environments, where a single erroneous step can waste limited interaction budget or cause irreversible effects before task failure becomes apparent. Reliable deployment therefore requires step-level confidence estimation: estimating, before execution, the probability that a proposed action will advance the task. Existing LLM confidence estimators are typically designed for static question answering under a fixed task context and evaluation criterion. For an agent, however, its action productivity depends on an environment transition that is observed only after execution. To address this challenge, we introduce Critic Experience Bank (CEB), a training-free framework that turns feedback from completed trajecto