Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does

arXiv:2608.19515v3 Announce Type: replace Abstract: Prosodic cues can carry task-relevant information that words omit, but existing benchmarks rarely test whether it changes downstream decisions. We introduce Hear2Act, a 480-scenario protocol with unstated user needs and verifiable task success. Across matched scenarios, we keep the task and user needs fixed, varying whether an unmet need is stated in words or absent from the transcript while the user's reaction is conveyed through prosody, yielding Explicit lexical and Prosody-mediated conditions. We vary assistant access to transcript, audio, and an indication of whether the recommendation is resolved, and evaluate two audio-capable LLMs and five text LLMs on behavior and task outcomes. Our results show an asymmetry: prosodic information is valuable when the need is absent from the transcript, but adds little when that need is stated in words. Yet neither audio-capable LLM benefits much from raw audio: adding audio to the transcript changes task success only from 14.3% to 15.1%. When models infer from audio whether the recommendation remains unresolved and use that inference with the transcript, success rises to 39.6%, close to 40.5% with ground-truth state. This reveals a perception-action gap: raw audio barely helps, while making the information explicit in text enables much better decisions.