Hear2Act is introduced, a unified evaluation protocol for text and spoken assistants with 480 persona-grounded scenarios, hidden user concerns, and objectively verifiable outcomes that show that prosody matters when lexical evidence is insufficient, and that audio-capable LLMs can recover information from speech but do not reliably carry it into action without an explicit intermediate representation.
Abstract
Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged. Yet existing benchmarks typically evaluate prosodic perception, response appropriateness, and task-oriented dialogue in isolation, making it difficult to test whether prosodic evidence changes downstream decisions. We introduce Hear2Act, a unified evaluation protocol for text and spoken assistants with 480 persona-grounded scenarios, hidden user concerns, and objectively verifiable outcomes. For each scenario, we keep the task and user needs fixed while varying whether the same concern is conveyed explicitly in words or primarily through prosody, and evaluate decisions under transcript, audio, and concern-state access. Using Hear2Act, we evaluate two audio-capable LLMs. Under Prosody-mediated feedback, adding audio to the transcript changes the average optimal-solution rate only from 14.6% to 15.3%. In contrast, when models infer the concern status from audio, represent it in text, and use it for next-action selection, the rate rises to 39.6%, close to 40.7% with the ground-truth state. This contrast, however, largely disappears under Explicit lexical feedback, where the concern is verbally mentioned in the utterance. Together, these results show that prosody matters when lexical evidence is insufficient, and that audio-capable LLMs can recover information from speech but do not reliably carry it into action without an explicit intermediate representation.
Overall, matched-text speech delivery should be treated as a first-class factor in Audio LLM safety evaluation by holding transcript content fixed and varying six speech-delivery presets whose acoustic attributes may co-vary.
It is found that responses in the expected target direction are frequently accompanied by changes outside descriptor-specific signal-level target sets, and the accompanying changes differ substantially across systems.
With the growing scale of multi-agent architectures and large language models, deployed AI assistants are increasingly tasked with reasoning over long, continuous, multi-session conversation histories. Current benchmarks evaluate this dialogue history as information retrieval over long horizon, temporal reasoning, or knowledge updates, while crucially ignoring the fundamental dynamics of human-agent interaction, i.e. how they said it. To address this gap, we present VoiceLongMemEval (VLME) benchmark, where every answer depends on paralinguistic metadata (emotion labels, prosody descriptors, and voice events) attached to conversational turns, which is otherwise unrecoverable from the words alone. Every item passes a three-stage adversarial gate, ensuring that a strong language model fails when given only the transcript. Evaluating leading frontier and open-weight models reveals a pervasive affect gap; providing text-track paralinguistic metadata yields a 0.09 to 0.38 accuracy boost (0.61 to 0.69 when prompted with evidence hints), while standard ASR pipelines systematically discard this signal. Additionally, audio-native models successfully extract these cues directly from speech (0.354 to 0.412 vs. 0.325 blind). Code and dataset will be made available upon acceptance.
Spoken dialogue state tracking recovers slot-value pairs from speech, where ASR errors concentrate in entity values and persist across turns, making it both a generation and an editing problem. A strong per-turn text editor corrects much of this but, operating on the transcript alone, leaves three recoverable errors: a value predicted inconsistently across turns, an omitted slot, and a value the audio does not support. We present AVERT, which scores each candidate value by combining cross-turn agreement with a trained audio-conditioned verifier and resolves the three error types with three operators, vote, add, and swap, each restricted to the slots where its error is common. On SpokenWOZ, a base speech-LLM reaches 33.04 JGA, a text editor 38.34, and AVERT 40.13, without retraining either. This is in the range of a 1B end-to-end system that consumes the full spoken history (39.32), though AVERT uses two 1B decoders rather than one. The audio verifier contributes a statistically significant gain, and restricting each operator to a selected slot subset matters: removing it lets unrestricted voting overwrite correct categorical values and fall below the editor.
Expressive speech systems have to decide how an utterance is delivered before any waveform is rendered. In dialogue agents, narration, and role-conditioned TTS, that planning step sets affect, pitch, energy, rate, pause, emphasis, and stance, yet standard audio metrics rarely show whether those choices were actually licensed by the source record. This leaves a practical evaluation gap: a system may sound plausible while relying on a memorized script instead of the cue that governs delivery. VoxReason casts this pre-synthesis step as a listener-free task for source-grounded speech planning. Systems output a source-cited speaking plan, and a deterministic verifier checks citation legality, slot agreement, unsupported state, schema validity, and one-cue counterfactual locality. On 1,440 checked source-label cases, shortcut controls show why slot accuracy alone is unsafe: a key-lookup oracle reaches 1.000 plan-slot accuracy on seen keys, while an emotion prior still reaches 0.958 slot accuracy on source-key-disjoint cases without citing intensity or identity. In a separate 100-case learned source-key-disjoint comparison, a 7B locality SFT+CF repair improves plan-slot accuracy/locality from 0.684/0.141 to 0.919/1.000, and removing source records lowers citation-required grounded score by 0.488. The resulting benchmark isolates whether planned delivery is warranted by the record before waveform evaluation or listener studies are used.
Complex acoustic problems may require models to perform acoustic operations, interact with external tools and reason over the resulting textual or processed-audio observations rather than answer directly from a fixed audio input. We study such problems as tool-interactive audio reasoning and develop SpeechAgent-R, an audio agent that coordinates its intrinsic multimodal understanding with external skills and tools. To support this capability, we construct HIU-Corpus, comprising 65,492 interaction trajectories and 507.6 hours of audio across 24 tasks, 8 skills and 9 tools. SpeechAgent-R first learns structured interaction behaviors through trajectory-based supervised fine-tuning and then improves its decisions through multi-turn reinforcement learning. We further introduce HIU-Bench to jointly evaluate task performance, interaction quality and generalization to diverse task settings. It contains 1,395 samples across 56 tasks, including in-distribution (ID) and out-of-distribution (OOD) splits with substantial shifts in tool usage and workflow composition. SpeechAgent-R achieves 84.17 on ID tasks and 70.94 on OOD tasks, improving over the base model under the same agent harness by 15.40 and 14.23 points. These results demonstrate that learning skill and tool coordination improves audio agents'ability to handle diverse task settings and adaptive tool interactions.
Yuwen Wang, Tian-Hao Zhang, Ming Cai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
