- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes NEST, which trains a continuous latent reasoner to generate complete answers from multiple prefixes of a shared reasoning trajectory. Each latent step feeds the previous position’s last-layer hidden state back as the next input embedding. Training combines multi-depth answer cross-entropy with teacher-based candidate-answer distribution distillation, alignment to teacher reasoning-step representations, and a penalty for increasing teacher–student discrepancy at greater depths. After freezing the reasoner, the authors train an initial-depth predictor and a confidence head, then select an acceptance threshold using held-out calibration data. During inference, the system generates an answer at an accepted endpoint, continues latent computation if confidence is insufficient, or falls back to explicit chain-of-thought reasoning.
Critical strengths
-
Clear problem formulation. The paper focuses on whether intermediate latent states can produce reliable answers, an important requirement for effective early stopping.
-
Evidence of improved shallow-prefix accuracy. Fixed-depth evaluations and matched-router comparisons show that multi-depth answer supervision improves accuracy at early latent endpoints.
-
Favorable inference efficiency. NEST achieves competitive accuracy with lower measured inference cost across the evaluated benchmarks and backbones. Applying Core NEST to CODI and SIM-CoT also improves their accuracy–inference-cost trade-offs.
Critical weaknesses
-
Limited methodological novelty. NEST retains Coconut-style latent recurrence and adds complete-answer supervision at multiple depths of the same trajectory. The core contribution is a straightforward application of deep supervision to an existing latent reasoning framework, offering limited conceptual novelty.
-
Insufficient validation of the depth-selection target. The target in Eq. (3) identifies a depth that preserves the teacher’s preferred answer within a finite candidate set. Its relationship to the earliest depth at which the student can generate a correct answer remains unestablished, particularly when the teacher is incorrect or the student answers correctly despite disagreeing with the teacher’s candidate distribution. The depth-prediction metrics in Tables 14 and 18 measure agreement with this proxy itself, without directly validating whether it reflects the computation actually required for correct answer generation.
-
Incomplete experimental reporting and offline cost accounting. The manuscript does not specify the concrete data-split sizes, key calibration settings, or the source and target distributions used in the task-shift evaluation, making these experimental conditions difficult to reconstruct. The training-cost totals in Table 19 also explicitly exclude offline candidate-pool preprocessing, which is required to construct the method’s supervision. The full offline computational cost therefore remains unquantified.
-
Poor readability of tables and figures. The font in Table 1 is excessively small. Figures 1 and 2 appear to have been generated directly by AI. Clear vector versions should be provided; if AI was used to generate these figures, this should be explicitly disclosed in the AI Use Statement.
Questions for authors
See the weaknesses above.
9 comments
addition
2. Regarding the validity of the depth-selection target , we agree with your observation that the teacher-consistency depth is not equivalent to the earliest depth at which a correct answer can be generated.
In Equation (3), is defined through the teacher's decision preferences over a finite candidate set . It measures the depth at which the student first satisfies a sufficient condition for preserving the teacher's candidate ranking. Therefore, it is a teacher-consistency proxy and does not directly guarantee that the student can generate a correct answer at that depth.
Discrepancies between these two depths may arise when the teacher produces an incorrect answer, when the student produces a correct answer but disagrees with the teacher's ranking, or when the correct answer is absent from the candidate set.
Accordingly, we explicitly refer to as the teacher-consistency depth proxy.
We introduce a separate diagnostic definition to directly analyze the earliest correct-answer depth:
,
where denotes the answer obtained by fully decoding the student at depth . Samples for which none of the five depths produces a correct answer are recorded separately.
We can establish an important mathematical constraint. In Table 5, the fixed-depth accuracy at is 76.43%, whereas Table 14 reports that the proportion of samples with is 15.8%.
Under a common evaluation distribution and depth-decoding protocol, we have and .
The difference between these marginal probabilities implies:
.
This provides a rigorous upper bound on the overall label agreement rate.
Using the complete marginal distributions over the five valid depths, we can derive an even tighter upper bound of 25.25% for the exact-match event in which both variables correspond to valid computational depths. This further demonstrates that the teacher-consistency depth proxy and the earliest correct-generation depth are not equivalent targets.
The 68.4% exact-match accuracy reported in our experiments refers to the capacity predictor's accuracy in predicting the proxy labels, rather than its accuracy in predicting .
We therefore explicitly distinguish two evaluation metrics:
- Proxy-label prediction accuracy: Whether the capacity predictor can accurately predict the teacher-consistency labels.
- Correctness-depth agreement: The degree of agreement between the teacher-consistency proxy and the actual earliest correct-generation depth.
We agree that only full-answer decoding at all five depths on a common diagnostic set can directly establish the exact-match rate between and , the proportion of underallocated computation, and the differences between cases in which the teacher is correct and incorrect.
Therefore, we have supplemented our evaluation with a five-depth full-answer decoding diagnostic, as presented in Supplementary Table 1. Due to the comment length limit, the supplementary tables will be presented in our final comment.
The results show that the exact agreement rate when both variables correspond to valid depths is 15.67%, whereas the nominal categorical agreement rate, which merges the two distinct special states into a common encoded category, is 22.89%.
These results confirm that substantial discrepancies exist between the teacher-consistency proxy and the earliest correct-generation depth.
However, NEST does not require the teacher-consistency proxy to exactly match the earliest correct depth. Instead, this proxy serves as an auxiliary supervision signal for training the capacity predictor, while the final execution decisions continue to rely on student-side confidence estimation and independently calibrated thresholds.
Through this additional analysis, we hope to clarify the role and limitations of the proxy objective, as well as its relationship to the actual adaptive execution mechanism.
addition
3. Regarding data splits, calibration settings, task distribution shifts, and offline computational costs, we sincerely thank you for identifying shortcomings in the reproducibility of our experiments.
Although we explained the principle of data separation across different training stages, we did not sufficiently specify the exact split sizes, calibration parameters, or the construction of task distribution shifts. Furthermore, the scope of offline computational costs reported in Table 19 was not fully explained.
These issues primarily resulted from insufficient descriptions of our experimental implementation details. We sincerely apologize for these omissions and would like to provide the following clarifications.
Regarding data splits and the joint training protocol, our experiments jointly train a single shared NEST model using six training data sources: GSM8K, MATH, MAWPS/ASDiv-A, AQuA-RAT, PrOntoQA, and ProsQA.
After training, the same model is evaluated consistently on eight benchmarks: GSM8K, MATH-500, SVAMP, BBH, MultiArith, AQuA-RAT, PrOntoQA, and ProsQA. The evaluation metrics are averaged with equal weight across the eight benchmarks.
In our experimental setup, BBH and MultiArith are reserved exclusively for testing. They do not participate in hierarchy training, router fitting, or threshold calibration. This allows us to examine cross-task performance without supervised adaptation to these target tasks.
Here, out-of-distribution evaluation is defined relative to the supervised training sources used in our experiments.
We divide the data into four mutually disjoint roles: hierarchy training, router fitting, calibration, and final evaluation.
Hierarchy training contains 10,400 samples, while router fitting and calibration each use 3,000 independent samples. The complete test sets across the eight evaluation benchmarks contain 11,484 samples in total. The detailed data splits are provided in Supplementary Table 2, which will be presented in our final comment due to the comment length limit.
Regarding potential data leakage, we paid particular attention to the historical overlap risk between MAWPS and MultiArith. Accordingly, our data-cleaning procedure includes test-question exclusion, matching of original and normalized question texts, mathematical-expression matching, and template-level near-duplicate detection. These procedures are intended to ensure that MultiArith test questions do not enter supervised training through other data sources.
Offline candidate-answer generation reads only the question texts and does not use test-set answers for candidate generation, filtering, or ranking. The independent calibration set is not used to update the parameters of the student model or the execution prediction modules.
Regarding threshold calibration and finite-sample risk control, our calibration setup independently selects 500 records from each of the six training sources, forming a balanced independent calibration set containing 3,000 samples.
The acceptance threshold is selected from a predefined set of 101 candidate values, ranging from 0.00 to 1.00 with a step size of 0.01. We set the confidence parameter to and the system-level unsafe risk budget to .
Here, unsafe risk is defined as the probability that the system accepts a latent-state answer and that the accepted answer is incorrect:
.
The conditional error rate among accepted samples is defined as:
.
According to Equation (11), for independent calibration records sampled with predefined quotas across the six tasks and a finite set of predefined thresholds, the following inequality holds simultaneously for all candidate thresholds with probability at least :
.
When , , and , the Hoeffding correction term is:
.
Therefore, a threshold satisfying the risk budget must satisfy:
.
Consequently, among the 3,000 calibration records, at most 373 accepted-and-incorrect events are permitted.
Throughout the calibration process, only the final acceptance threshold is updated. The student model, capacity predictor, and confidence prediction head remain frozen, and test-set labels are never used for threshold selection.
Reply
Response to Reviewer
We sincerely thank you for your valuable and constructive comments. Some of the issues you raised stem from aspects that we overlooked, while others resulted from insufficient clarity in our presentation. We would therefore like to address your concerns one by one below. We hope that our responses will resolve your questions and further demonstrate the merits and contributions of our work.
1. Regarding the novelty of NEST, we agree with your observation that deep supervision and Coconut-style continuous latent-state recurrence are both important foundations established by prior research. The contribution of our work is not to reinvent these techniques, but rather to address a specific problem in adaptive continuous latent-state reasoning: the fact that an intermediate state can support further computation does not necessarily mean that it is already capable of independently generating a correct answer.
Conventional terminal-only supervision primarily optimizes predictions at the final computational depth. In contrast, NEST requires multiple prefixes along the same recurrent trajectory to simultaneously fulfill two roles: generating a complete answer at the current depth while preserving the ability to continue deeper latent-state reasoning.
To achieve this, we first employ Core NEST to supervise complete-answer generation at different depths, then introduce decision distillation, ordered state alignment, and monotonic constraints, and finally train and calibrate the execution policy independently. This staged design allows us to directly examine the respective contributions of endpoint competence and the dynamic execution policy.
Table 5 shows that, at K=1, Terminal-only, Core NEST, and Full NEST achieve accuracies of 67.63%, 73.58%, and 76.43%, respectively. Core NEST improves accuracy by 5.95 percentage points at K=1, but by only 0.08 percentage points at K=16. This indicates that endpoint supervision primarily shifts answer-generation competence toward shallower computational states.
Table 2 further shows that, under the same router, Terminal-only, Core NEST, and Full NEST achieve average depths (Avg.K) of 8.90, 6.55, and 5.30, respectively, with corresponding relative GPU costs (Rel.GPU) of 0.520, 0.455, and 0.402.
Therefore, we emphasize that NEST's contribution lies in training anytime answer endpoints along shared continuous latent-state trajectories. We do not claim that multi-depth supervision or recurrent architectures themselves are fundamentally new techniques introduced by our work.