- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents DeIRD, a decoupled implicit reasoning framework for spoken dialogue models. The goal is to reduce the latency caused by explicit Chain-of-Thought (CoT) generation while improving reasoning and dialogue performance.
The framework consists of three main components. First, a text VAE compresses variable-length CoT sequences into fixed-length continuous latent representations. Second, DMIR, built on DIFFA-2, predicts these latent representations directly from speech using an iterative confidence-guided mask-predict strategy. Finally, a Latent Flow Adapter (LFA) maps the predicted latents into the hidden space of the downstream dialogue model, where they serve as soft prompts to guide response generation.
The authors also construct LatentReason-40k, a dataset containing 46,809 samples, and evaluate their approach on three spoken dialogue models with different architectures: Step-Audio-2-mini, VITA-Audio, and Kimi-Audio.
The results show that DeIRD generally outperforms the evaluated explicit CoT baselines on dialogue and reasoning benchmarks while substantially reducing time to first audio. The paper also includes ablation studies on the latent representations, decoding strategies, and the LFA module to examine their contributions.
Critical strengths
A useful performance–latency trade-off across speech model architectures. DeIRD uses an audio-conditioned Mask-Predict module to generate fixed-length continuous reasoning representations, reducing the delay of explicit CoT generation. On Step-Audio-2-mini, it improves the OpenAudioBench average from 55.7 to 62.6 while reducing time to first audio from 18.6 to 1.50 seconds relative to explicit CoT fine-tuning, with matched downstream training data and epochs. Its evaluation on three backbones covering both interleaved and parallel generation also supports its applicability beyond a single model architecture. Together, these results demonstrate the practical value of the proposed framework.
Critical weaknesses
-
The contribution of CoT supervision is not adequately isolated. Appendix D provides evidence that instance-specific latents are useful, but does not establish that intermediate reasoning information is what makes them useful. The paper lacks a standard SFT baseline trained on the same question–answer pairs without CoT or latents, and a matched comparison against answer-only latent targets. These omissions leave the incremental benefit of CoT supervision unresolved: the gains may partly reflect task adaptation and answer-related knowledge distillation rather than the proposed reasoning mechanism. This attribution gap directly weakens the paper’s central claim.
-
The defining iterative mechanism lacks a convincing performance–cost justification. DMIR requires 32 sequential prediction rounds, accounting for approximately 1.39 seconds of the reported 1.50-second TTFA. Yet the paper does not compare it against a matched single-pass predictor of the same latent targets. The Top-1/2/4 ablations demonstrate trade-offs among iterative configurations, but do not establish whether iteration is preferable to direct latent prediction. Consequently, outperforming lengthy explicit CoT generation does not adequately justify the computational expense of the paper’s central design. Moreover, improved GSM8K Pass@k alone does not substantiate the stronger claim of greater reasoning-path diversity.
Questions for authors
-
Gain beyond standard SFT — requested comparison. Could the authors report a standard SFT baseline using the same question–answer pairs, backbone, and downstream training configuration, but without CoT or latent inputs? The controls in Appendix D are informative, but do not directly establish the incremental benefit of DeIRD over ordinary supervised adaptation.
-
Value of intermediate reasoning supervision — requested comparison.How does full-CoT supervision compare with answer-only latent targets under matched latent shape, model capacity, and training conditions? This comparison would help determine whether intermediate reasoning information provides a benefit beyond answer-related knowledge distillation, which is central to the paper’s interpretation of its results.
-
Benefit of iterative prediction — requested comparison.Could the authors compare the default 32-round DMIR with a single-pass latent predictor, using the same backbone and latent targets and appropriately training the downstream model for each setting? Please report both downstream accuracy and TTFA. Since DMIR contributes approximately 1.39 seconds of the reported 1.50-second latency, this comparison is important for assessing whether iterative prediction justifies its additional cost.
-
Evidence for reasoning diversity — clarification.Where does stochasticity enter the GSM8K evaluation: latent generation, downstream answer decoding, or both? Given Algorithm 1’s deterministic slot selection and mean commitment, what evidence links the Pass@k improvements specifically to more diverse latent reasoning paths, rather than improved answer accuracy or downstream sampling? Please clarify the scope of the diversity claim supported by the current results.
4 comments
Response to Reviewer jNDt(2/2)
3. Clarifying and directly evaluating reasoning diversity (W2 & Q4)
We clarify our hypothesis: continuous reasoning states can retain information about multiple candidate continuations. Greedy textual decoding feeds back only one selected token at each step, whereas continuous feedback allows information about alternative paths to be retained before committing to discrete text.
This hypothesis is supported by prior work. Coconut [1, Section 4.3] analyzes intermediate continuous states and finds behavior consistent with retaining alternative branches. Soft Thinking [2, Section 3.2] explicitly feeds back probability-weighted token embeddings. Reasoning by Superposition [3] provides a theoretical construction in which continuous states simultaneously encode multiple search frontiers for graph reachability. Together, these studies support the representational basis of our hypothesis.
To examine this hypothesis in DeIRD, we conduct a paired diagnostic on 100 randomly selected GSM8K questions, using the same trained Step-Audio-2-mini checkpoint throughout. We directly supply three controlled explicit reasoning trajectories or DMIR-generated continuous latents before answer generation. Each explicit trajectory contains a designated branch point: it follows the correct branch, follows an incorrect branch, or initially follows an incorrect branch before backtracking once and switching to the correct branch. The supplied textual trajectories exclude the final answer.
This experiment is included in Section 4.2 and Table 3, with its analysis in Section 4.4, Finding 5, of the revised manuscript.
Table R3.
| Condition | Intermediate reasoning supplied to the backbone | Pass@1 accuracy (%) ↑ |
|---|---|---|
| Correct single-path CoT | Correct branch → correct reasoning continuation | 76.0 |
| Incorrect single-path CoT | Incorrect branch → incorrect reasoning continuation | 24.0 |
| CoT with backtracking | Incorrect branch → backtrack → correct continuation | 87.0 |
| DeIRD | DMIR-generated continuous latents | 89.0 |
DeIRD achieves accuracy comparable to explicit CoT with backtracking, without requiring textual correction trajectories. These results support the hypothesis that continuous reasoning can retain useful alternatives and avoid premature commitment to discrete reasoning choices.
[1] Hao et al., Training Large Language Models to Reason in a Continuous Latent Space, COLM 2025.
[2] Zhang et al., Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space, arXiv 2025.
[3] Zhu et al., Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought, NeurIPS 2025.
Kind Follow-up on Our Response
Dear Reviewer jNDt,
Thank you for your thoughtful review. We have posted a response to your comments, together with the new experimental results and references to the corresponding changes in the manuscript.
We appreciate the demands on your time during the discussion period. When you have a chance to read our response, we would welcome your feedback on whether it resolves the concerns you raised.
If any point needs further clarification, we would be happy to address it before the discussion closes.
Best regards,
The Authors
Kind Follow-up on Our Response
Dear Reviewer jNDt,
Thank you for your thoughtful review. We have posted a response to your comments, together with the new experimental results and references to the corresponding changes in the manuscript.
We appreciate the demands on your time during the discussion period. As the discussion period is drawing to a close, we would be grateful if you could review our response when you have a chance and let us know whether it addresses the concerns you raised.
If any point needs further clarification, we would be happy to address it before the discussion closes.
Best regards,
The Authors
Response to Reviewer jNDt(1/2)
Thank you for the constructive feedback.
Thank you for acknowledging the instance-specific latent controls in Appendix D. We supplement these experiments with two baselines:
The additional comparisons on reasoning-specific metrics are reported below.
Table R1. Results are reported as S / V / K: Step-Audio-2-mini, VITA-Audio-Plus-Vanilla, and Kimi-Audio-7B-Instruct.
DeIRD outperforms Standard QA SFT on every reported metric across all three backbones. Compared with Answer-only latent, it improves VoiceBench BBH by 3.4 / 3.7 / 2.2 points and OpenAudioBench Reas. by 0.07 / 0.17 / 0.22 points.
These results indicate that the gains cannot be explained solely by ordinary task adaptation or answer distillation. They support intermediate reasoning supervision as an important source of improvement, providing additional benefits beyond answer-related knowledge distillation.
Thank you for your assessment of the Top-2 and Top-4 ablations, reported in Table 1, Ablation 4, and discussed in Section 4.4, Finding 4. We additionally trained a single-pass Top-32 predictor that generates and commits all 32 latent slots in one forward pass. We then adapted each of the three downstream backbones using its predicted latents.
Table R2. Results are reported as S / V / K: Step-Audio-2-mini, VITA-Audio-Plus-Vanilla, and Kimi-Audio-7B-Instruct.
Although single-pass prediction reduces TTFA, it underperforms even Random Noise Latent on GSM8K and OpenAudioBench across all three backbones, supporting the substantive value of iterative prediction.
As specified in Section 4.2, “Ablation Studies,” the noise control uses random representations sampled near the expected vocabulary embedding space. We hypothesize that accepting all slots simultaneously, without confidence-guided sequential commitment and conditioning updates, can produce latents whose embedding distribution deviates from this space and introduces misleading task information.