Dialogue Telemetry: Turn-Level Instrumentation for Autonomous Information Gathering
This addresses an instrumentation gap for autonomous systems conducting dialogues, offering a practical tool for monitoring efficiency, though it is incremental as it builds on existing dialogue and RL methods.
The paper tackles the problem of monitoring efficiency in autonomous information-gathering dialogues by introducing Dialogue Telemetry, a framework that provides turn-level signals to detect unproductive questioning, validated in simulations where it improved policy performance.
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.