AURAL is introduced, which models a distribution over multiple plausible reasoning continuations in latent space and jointly predicts chunks of future states to reduce sequential forward passes and reasoning latency and shows that harder questions elicit more latent reasoning steps.
Abstract
Model intelligence and fast response jointly shape the quality of interaction with speech language models, yet remain difficult to achieve together. Explicit chain-of-thought (CoT) improves reasoning and audio understanding, but generating intermediate reasoning tokens delays responses. Describing fine-grained acoustic cues further lengthens CoT and increases latency. Latent reasoning can reduce this overhead, yet existing methods often trail CoT and remain limited by single-path supervision and reasoning budgets that do not adapt to problem difficulty. We introduce AURAL, which models a distribution over multiple plausible reasoning continuations in latent space and jointly predicts chunks of future states to reduce sequential forward passes and reasoning latency. To provide initial supervision for latent reasoning, we construct AuralReason-683K: 683K bilingual speech utterances (about 1,000 hours) with concise CoT for emotion recognition, empathetic dialogue, and general reasoning. AURAL-RL then explores beyond these traces, rewarding concise reasoning that yields high-quality answers and adapting reasoning effort to each problem. Across two backbones, AURAL-RL achieves performance comparable to CoT-RL, with larger gains over the respective supervised checkpoints on most metrics. Analysis further shows that harder questions elicit more latent reasoning steps. On Qwen2.5-Omni, it reduces time to the first answer token by 11.8x, from 1.22 to 0.10 s, versus 0.05 s for direct answering.
JELAR, a Joint-Embedding Predictive Architecture (JEPA)-based latent reasoning framework that conditions latent reasoning supervision on acoustic representations learned from raw waveforms, demonstrates the effectiveness of JEPA-conditioned latent reasoning as an alternative to explicit textual CoT supervision.
Donghang Wu, Haoyang Zhang, Yizhou Peng et al.· 0 citations
Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evidence. Textual chain-of-thought reasoning can partially mitigate this issue by encouraging models to decompose visual questions into intermediate evidence-seeking steps, b...
This work first adapts the model to the domain using supervised fine-tuning on synthesized spoken question-answering data and shows that RL improves the accuracy on GSM8K beyond levels previously achieved for speech models only with supplementary reasoning traces, and establishes a new state-of-the-art for mathematical...
Large audio language models answer questions about speech, sound, and music, yet their accuracy drops sharply on tasks that need fine-grained acoustic analysis. Judging which of two speakers has the higher pitch demands iterative signal-level reasoning that a content question does not. Current models spend the same com...
LoopSLM builds on looped Transformers for latent reasoning, reusing a decoder block to refine hidden states with acoustic grounding at every pass, and further narrows the perception-reasoning gap by separating learning to reason from learning to respond, enabling direct inference without CoT.
VITAL is an importance-guided hybrid reasoning framework that selectively verbalizes informative tokens as reasoning anchors while keeping most computation latent, and achieves higher reasoning accuracy with substantially shorter reasoning trajectories on Qwen3-1.7B.
Zhe-Hao Zhou, Tong Su, Sheng-Yu Zhu et al.· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
MIT News · Artificial Intelligence· news.mit.eduAug 27, 2026
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.