Autonomous systems conducting schema-grounded information-gathering dialogues face an instrumentation gap, lacking turn-level observables for monitoring acquisition efficiency and detecting when questioning becomes unproductive. We introduce Dialogue Telemetry (DT), a measurement framework that produces two model-agnostic signals after each question-answer exchange: (i) a Progress Estimator (PE) quantifying residual information potential per category (with a bits-based variant), and (ii) a Stalling Index (SI) detecting an observable failure signature characterized by repeated category probing with semantically similar, low-marginal-gain responses. SI flags this pattern without requiring causal diagnosis, supporting monitoring in settings where attributing degradation to specific causes may be impractical. We validate DT in controlled search-and-rescue (SAR)-inspired interviews using large language model (LLM)-based simulations, distinguishing efficient from stalled dialogue traces and illustrating downstream utility by integrating DT signals into a reinforcement learning (RL) policy. Across these settings, DT provides interpretable turn-level instrumentation that improves policy performance when stalling carries operational costs.

翻译：执行模式驱动信息收集对话的自主系统面临监测缺口，缺乏用于追踪信息获取效率及检测提问何时失效的轮次级可观测指标。本文提出对话遥测（DT）框架，该测量体系在每次问答交互后生成两个与模型无关的信号：（i）进度评估器（PE），用于量化各类别的剩余信息潜力（提供基于比特的变体）；（ii）停滞指数（SI），用于检测可观测的失效特征——即对同一类别反复提出语义相似、边际收益极低的追问。SI无需因果归因即可标记此类模式，适用于难以确定性能退化具体原因的监测场景。我们在受搜救（SAR）任务启发的受控访谈中，基于大语言模型（LLM）仿真验证DT框架，成功区分高效对话轨迹与停滞对话轨迹，并通过将DT信号集成至强化学习（RL）策略中展示其下游应用价值。实验表明，DT提供的可解释轮次级监测指标能有效提升策略性能，尤其在停滞行为产生操作代价的场景中。