- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies data-free model merging for long-to-short reasoning. The main motivation is to transfer useful reasoning ability from a long-CoT model to a short-response model without requiring additional training data, activation statistics, or an inference-time controller. The proposed method, BCL-Merge, constructs two layer-wise parameter-space scores. The first is a strength score based on the relative magnitude of the long-CoT task vector, intended to measure the amount of transferable reasoning signal. The second is a conflict score based on the fraction of parameter coordinates for which the short and long task vectors have opposite signs, intended to measure the risk of disrupting short-model behavior. The two scores are combined as . Layers are ranked using this score, a top- subset is selected according to a reasoning budget, and layer-wise merging coefficients are assigned through an entropy-regularized allocation objective. The method is evaluated mainly on mathematical reasoning benchmarks across several model sizes and backbones. The reported results show competitive accuracy-length trade-offs and, in several settings, outperform existing merging baselines while substantially reducing response length relative to the long-CoT model.
Critical strengths
-
Practical and simple data-free formulation. The paper targets a relevant problem: reducing unnecessary long-CoT reasoning while retaining useful reasoning capability. BCL-Merge does not require additional training data, activation statistics, or an input-dependent inference controller, which makes the method simple and potentially useful in practice.
-
Competitive empirical accuracy-length trade-off. The reported empirical results are consistently competitive across multiple model sizes and backbones. In particular, the method often improves over existing merging baselines while substantially reducing response length relative to the long-CoT model. This suggests that the proposed merging strategy is empirically useful even though I have concerns about its interpretation.
Critical weaknesses
1. The semantic interpretation of the two proposed scores is not sufficiently validated.
The central conceptual claim of the paper is that the relative magnitude of the long task vector represents transferable "reasoning strength", while sign disagreement between the short and long task vectors represents harmful "conflict". However, the current experiments mainly show that using these two scores leads to a strong final merged model; they do not directly establish that the scores actually measure the quantities claimed by the paper.
For example, if the strength score truly reflects transferable reasoning capability in a given layer, a more direct validation would be to intervene on or merge individual layers and test whether the strength score correlates with the actual improvement in hard-task reasoning accuracy. Similarly, if the conflict score is intended to measure the risk of disrupting short-model behavior, the paper should test whether it predicts the actual behavioral degradation caused by injecting the corresponding long-model layer into the short model.
Without such direct evidence, it is difficult to determine whether the proposed scores reveal a genuine parameter-space mechanism or simply constitute an empirically effective layer-ranking heuristic.
This concern also affects my assessment of the theoretical contribution. The appendix introduces assumptions that connect long-update magnitude to a latent reasoning component, but these assumptions partially encode the very relationship that should be validated. Likewise, once is defined in advance, adding entropy regularization naturally leads to a top-/softmax-style allocation. Therefore, I view the current theory more as an interpretation of the proposed rule than as independent evidence supporting the claimed reasoning mechanism.
2. The current evaluation does not sufficiently establish that the proposed method is better than simpler alternative heuristics, nor does it fully support the paper's broad framing.
Although the paper evaluates multiple model scales and several mathematical reasoning benchmarks, most experiments repeatedly measure mathematical reasoning accuracy and output length. This is reasonable for evaluating final performance, but it is relatively narrow compared with the paper's broader claims about general long-to-short reasoning and parameter-space "patterns".
More importantly, several simple alternatives appear insufficiently explored. Under exactly the same budget and coefficient-allocation setting, I would like to see systematic comparisons against:
- depth-only layer selection;
- raw long-update norm ranking;
- cosine similarity / negative inner product;
- magnitude-weighted sign disagreement;
- and other simple ways of combining the strength and conflict signals.
The current ablations show that the strength and conflict components are individually useful, but they do not establish that the specific formulation is necessary, nor that the emphasized parameter-space interpretation is unique or essential.
In addition, the visualization suggests that the selected layers are concentrated more heavily in the middle and deeper layers. This makes a simple depth-based baseline particularly important. If a depth-only heuristic can achieve similar results, the contribution of the proposed parameter-space scoring mechanism would be substantially weakened.
Questions for authors
1. Can the authors directly validate the semantic meaning of the proposed strength and conflict scores?
In particular, could you report whether the layer-wise strength score correlates with the actual reasoning gain obtained by intervening on or merging an individual layer, and whether the conflict score correlates with the actual degradation of short-model behavior? Such evidence would materially affect my assessment because it would help distinguish a genuine parameter-space mechanism from an empirically effective heuristic.
2. How does BCL-Merge compare with simpler layer-selection criteria under exactly the same coefficient-allocation and reasoning-budget setting?
I am particularly interested in comparisons with depth-only selection, raw long-update norm, cosine similarity / negative inner product, and magnitude-weighted sign conflict. If the proposed score provides a clear advantage over these alternatives, it would substantially strengthen both the novelty of the method and the credibility of its interpretation.
3. To what extent does the proposed layer ranking generalize beyond mathematical reasoning?
Most of the current evaluation is conducted on math-oriented benchmarks. If the same parameter-space criterion and layer ranking remain effective on qualitatively different reasoning domains, this would make the paper's broader framing of long-to-short reasoning considerably more convincing.
5 comments
Response to Reviewer Kmvc (2/2)
W2&Q2: Comparison with simpler layer-selection criteria.
Thank you for raising this important concern. Demonstrating the individual effectiveness of strength and conflict scores is not sufficient to establish the necessity of our specific formulation for layer selection. To address these concerns, we conduct an additional systematic comparison with several alternative layer-selection criteria, including depth-only selection, raw long-update norm ranking, cosine similarity, negative inner product, magnitude-weighted sign disagreement, and alternative combinations of the strength and conflict signals. All methods use exactly the same coefficient-allocation and reasoning-budget setting. Thus, the performance differences can be attributed to the layer-selection mechanism and detailed results are presented in table below.
| Selection criterion | Avg Acc. | Avg Len. |
|---|---|---|
| depth-only layer selection(Deepest layers) | 55.98 | 1833.3 |
| Raw long-update norm ranking | 54.97 | 2370.0 |
| Cosine similarity | 55.60 | 1968.3 |
| Negative inner product | 55.55 | 2088.3 |
| Magnitude-weighted sign disagreement | 57.13 | 1906.7 |
| Minimum score | 56.63 | 1852.5 |
| Ours | 57.80 | 1603.3 |
It can be summarized that:
(1) Depth alone is insufficient to explain the effectiveness of our layer selection. The depth-only baseline exhibits substantially inferior performance compared with our method, which indicates that the effectiveness of layer selection depends on the parameter-space characteristics captured by our proposed scoring mechanism, rather than the positional information of layers alone.
(2) Simpler layer-selection criteria like parameter-space similarity and magnitude-based criteria cannot replace our proposed scoring mechanism. These criteria do not explicitly capture the complementary roles of reasoning strength and short-answer conflict in the same manner as our formulation. Their inferior performance suggests that simply measuring update magnitude, directional similarity, or parameter disagreement is insufficient to identify the most beneficial layers. By contrast, our method provides a more informative criterion to identify layers by jointly considering the reasoning strength and short-answer conflict.
W2&Q3: Generalization beyond mathematical reasoning.
Thanks for your insightful advice! We totally agree that the ability beyond mathematical reasoning to different reasoning domains is crucial for the generalization ability. To this end, we choose HumanEval, MBPP and GLUE to evaluate the ability of code-generating and language-understanding. The performance are shown below.
| Method | HumanEval pass@1 | HumanEval Len. | MBPP pass@1 | MBPP Len. | GLUE | GLUE Len. |
|---|---|---|---|---|---|---|
| Short model | 63.41 | 440 | 62.40 | 380 | 80.59 | 36 |
| CoT model | 78.66 | 5600 | 70.20 | 3800 | 78.96 | 165 |
| TIES | 71.34 | 2200 | 68.40 | 1560 | 79.79 | 78 |
| DARE-TIES | 70.73 | 2050 | 67.40 | 1500 | 78.91 | 72 |
| Ours | 77.44 | 1900 | 71.00 | 1200 | 81.52 | 57 |
It can be seen that compared to existing methods, our mtehod obtains substantial improvements (+6.1%, +2.6% and +1.73%, respectively) with shorter responses, and even outperforms CoT model in MBPP and GLUE, which strongly showcase the effectiveness and generalization ability of the proposed method.
We have updated the manuscript in blue based on the valuable advice. Specifically, we add direct validation of strength and conflict scores in Tab.13, comparison with simpler layer-selection criteria in Tab.14, and generalization beyond mathematical reasoning in Tab.11. If you have any further questions, do not hesitate to contact us and we will try our best to solve them. Thank you again for your time and effort!
Looking Forward to Your Reply
Dear Reviewer Kmvc,
We truly appreciate your time and effort in reviewing our work. Following your insightful advices, we provide direct validation of strength and conflict scores, comparison with simpler layer-selection criteria, and generalization beyond mathematical reasoning to comprehensively demonsrtate the effectievess of our proposed method, which we believe have adequately adressed your concerns.
Could you please spend several minutes looking through our response and revised manuscript to see if there are any questions left about the work? If you have any remaining problems, respond to us at your convenience and we will try our best to address them.
Best wishes,
Submission 2713 Authors.
Response to Reviewer Kmvc (1/2)
Dear Reviewer Kmvc,
Thank you for your effort in reviewing our paper with constructive suggestions! We will answer each question respectively.
W1&Q1: Direct validation of strength and conflict scores.
Thank you for this insightful comment! Proposition 1 theoretically derives the optimal selection and allocation formulation in a general way by constructing a proxy objective, and we totally agree that further empirical validation is necessary to directly validate whether the proposed strength and conflict scores reflect actual model behavior, particularly reasoning benefits on hard tasks and potential degradation on tasks that can be solved with short answers, respectively.
To investigate these relationships, we conduct controlled layer-group intervention experiments following your suggestion. Specifically, we compare Top-K and Bottom-K layer groups according to three criteria: strength score Rl, conflict score Cl, and their combination Rl(1−Cl). Only the identities of the selected layers are changed, while other experimental settings remain fixed, allowing us to isolate the effects of different layer-selection signals.
Since the effectiveness can be reflected by different types of questions, we divide the performance evaluation into Easy and Hard subsets, which are defined according to the outcomes of the short outcomes (Tab.6): Short models answers every Easy example correctly and every Hard example incorrectly. This partition allows us to examine whether layer interventions improve reasoning on challenging examples while preserving the original model's ability to handle examples that do not require extensive reasoning. Results are summarized below.
We can conclude that:
(1) Strength scores correlate with reasoning improvements. Comparing Top-K and Bottom-K selection under Rl (row 1&2), selecting high-strength layers improves Hard accuracy from 54.4% to 71.0%, a substantial gain of 16.6%. Meanwhile, Easy accuracy remains unchanged with longer response. This suggests that layers with higher strength scores contribute more to difficult reasoning tasks, supporting our interpretation of Rl as a proxy for potential reasoning benefits.
(2) Conflict scores reflect short-answer disruption. Under the conflict criterion Cl, selecting Top-K layers (row 3&4) results in lower Easy accuracy (95.7% vs. 96.9%) and substantially longer Easy responses (2015 vs. 1040) compared with Bottom-K selection. This indicates that interventions on high-conflict layers are more likely to disrupt the model's ability to produce concise answers on tasks that the Short model can already solve. These observations reveal the interpretation of Cl as a proxy for potential short-answer disruption.
(3) Combining the two signals provides a better balance. The joint criterion Rl(1−Cl) explicitly favors layers with high reasoning strength and low conflict (row 5&6). Its Top-K selection achieves the best accuracy, while producing shorter responses, suggesting that the proposed two signals effectively balance reasoning improvements with the preservation of concise responses.