- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The model assigns probabilities to many possible answers. Some answers have high probabilities, while others have low probabilities. Power sampling “sharpens” this distribution. It makes high-probability answers stand out more and makes low-probability answers less likely to be chosen. This can improve reasoning performance, because the model is more likely to choose answers that it considers reliable.
This paper finds that different problems need different levels of sharpening. For problems where the model is confident and the correct answers have clearly higher quality than the wrong ones, stronger sharpening can help the model choose good answers more firmly. But for problems where the model is uncertain, or where correct and wrong answers are hard to separate, too much sharpening may push the model toward a wrong answer.
To solve this problem, the authors propose Adaptive Power Sampling, or APS. APS adjusts the sharpening strength for each problem during test time. It uses two signals: how much the sampled answers agree with each other, and how much reward the model gives to these answers itself. The results show that APS works better than ordinary power sampling with a fixed sharpening strength.
Critical strengths
The work uses experiments to clearly show why different problems need different degrees of sharpening.
The paper identifies an effective proxy metric for estimating how solvable each problem is for the model.
Critical weaknesses
undergoes multiple rounds of iterative updates, and a new sampling process is required after each update, which seems likely to increase the time overhead of the algorithm.
There are some writing issues and unclear descriptions in the paper. For example, in Table 1, some non-SOTA values are bolded. In addition, the introduction of sequence-level MCMC sampling is overly brief. Since this module plays an important role in the algorithm, introducing it only through citations make it difficult for readers to understand.
The paper conducts experiments only on models based on the Qwen2.5-7B architecture, lacking evidence for the generalizability of the proposed method.
The experimental analysis of the method is still limited to overall accuracy results, lacking ablation studies that specifically evaluate the effectiveness of individual APS components.
Questions for authors
How much inference time and sampling cost does APS require compared with other methods?
Does APS still work well on models with different architectures and sizes?
Why are the Power-SMC results reported in this paper different from those in the original paper [1]?
How would the results change if either or is removed from APS?
How would the results change if is not adapted? For example, multiple values could be used for sampling at the same time, and the final answer could be selected by voting.
[1] Azizi, Seyedarmin, et al. "Power-smc: Low-latency sequence-level power sampling for training-free llm reasoning." arXiv preprint arXiv:2602.10273 (2026).
4 comments
A Brief Follow-up on Our Response
Dear Reviewer ca5Q,
Thank you again for your careful review. Our response provides additional end-to-end inference latency comparisons and experimental results across different model architectures and sizes. We also clarify the writing issues you raised and explain the differences in the Power-SMC experimental setup. Furthermore, we discuss the role of answer agreement and present additional ablation studies with non-adaptive sampling strategies.
We would be grateful if, when convenient, you could let us know whether our response has addressed your main concerns and whether any further clarification would be helpful.
Best regards,
The Authors
Thank you for your response. However, I still feel that the algorithm's runtime efficiency remains a limitation. I will therefore keep my original score unchanged.
Further Response on Runtime Efficiency and Matched-Latency Results
Thank you for following up. Test-time scaling typically intends to improve reasoning accuracy by allocating additional inference time and computational resources. Thus, the key consideration is how effectively these resources are utilized to achieve meaningful accuracy gains. For example, self-consistency shows that sampling more reasoning paths can improve the accuracy of the voted answer (https://arxiv.org/pdf/2203.11171). The gains also depend on how the compute resources are allocated for each query (https://arxiv.org/pdf/2408.03314). In our work, APS uses this additional time to adapt the sharpening exponent to increase the reasoning performance. Specifically, it uses answer agreement and sequence log-likelihood from earlier responses to decide how strongly to sharpen the distribution for later samples, then votes among responses drawn at the selected exponent. We generate the samples within each round in parallel. Each subsequent round should wait for the preceding responses to update , introducing latency relative to fixed-exponent voting.
Accuracy gains beyond majority voting. As reported, APS achieves substantial improvements of 6.6, 5.5, and 4.0 percentage points over power sampling on MATH500, HumanEval, and GPQA, respectively. Even when fixed-exponent power sampling uses 12 responses, APS still gains 4.2, 4.3, and 3.0 points under the same response budget, accounting for 64%, 78%, and 75% of its total improvement over single-response PS. These gains are particularly meaningful given the strong voting baseline. To put these improvements into perspective, prior work on self-verification reports improvements of 1.2 and 3.0 percentage points over majority voting on MATH500 and AIME24, respectively, using a 16-sample budget (https://arxiv.org/abs/2506.01369), which provides useful context for the magnitude of our improvements. Overall, our results demonstrate that query-wise exponent adaptation provides meaningful accuracy gains beyond majority voting under the same response budget.
Matched-latency comparison. We further conduct a matched-latency comparison on MATH500 using Qwen2.5-Math-7B. Specifically, for each query, we first measure the end-to-end inference latency of APS with 12 responses. Then, we allocate the same time budget to fixed-exponent PS-voting, allowing it to generate the maximum number of responses within this budget. We report the mean of the per-query latency ratios, with APS as the reference. Meanwhile, we select the count using timing alone and use the same GPU, batched MH sampler, and KV cache policy for the methods.
| Method | Mean responses per query | Relative latency | Pass@1 |
|---|---|---|---|
| Fixed-exponent PS-voting (12-response reference) | 12 | 0.772 | |
| Fixed-exponent PS-voting (matched per query) | 17.9 | 0.776 | |
| APS | 12 | 0.814 |
From the results, even when PS-voting can spend the full APS time budget on each query and generate 17.9 responses on average, APS retains a 3.8 percentage point Pass@1 advantage. Under the same per-query time budget, using early responses to adapt the exponent yields significantly higher accuracy than drawing a larger pool at a fixed exponent. We will include this comparison in the revision, and we would appreciate your reconsideration in light of these results.
Response to Reviewer ca5Q
Thank you for your careful review. We believe the questions and suggestions you have raised are valuable and will help us improve this paper. Below are the authors’ clarifications regarding the issues you raised; we look forward to receiving your feedback.
1.Inference time and sampling cost (W1,Q1) We report mean end-to-end relative latency on Qwen2.5-Math-7B (normalized to single-response PS) after warm-up on a single GPU with batched parallel trajectories within each sampling round. We add PS-voting that generates 12 parallel responses at α=4 and selects the final answer by voting.
APS adapts α through sequential K=4 batches, which costs 2.48/2.32/2.65 times PS, and 1.80/1.76/1.87 times PS-voting. However, APS gains 6.6/5.5/4.0 percentage points over PS and 4.2/4.3/3.0 percentage points over PS-voting, which means APS's gain over PS-Voting makes up 64%/78%/75% of its total gain over PS. APS trades extra latency for substantial accuracy gains via test-time scaling.
2.Writing clarification (W2) Thank you for pointing these out. In the final version, we will underline only the best result per model/benchmark in Table 1 and add the MH acceptance rule and blockwise MCMC procedure to the appendix. These are the same in (https://arxiv.org/pdf/2510.14901).
3.Generalizability of APS (W3,Q2) Tables 1–2 show gains of APS on Qwen2.5-7B, Qwen2.5-Math-7B, DeepSeek-Math-7B and its RL variant. The Qwen models (7.6B parameters, 28 layers, a hidden dimension of 3584, and grouped-query attention with 28 query heads and 4 key/value heads) and DeepSeek-Math (6.9B parameters, 30 layers, a hidden dimension of 4096, and multi-head attention with 32 query heads and 32 key/value heads) differ in architecture and size. We further adopt Phi-3.5-mini-instruct (3.8B) and Qwen2.5-32B to show generalization across model sizes. Following the setup in the paper, the results are:
APS outperforms PS on all three benchmarks at both 3.8B and 32B, showing that its gains extend across model sizes.
4.Clarification of Power-SMC results (Q3) Power-SMC was first introduced by [1], while it uses block N=64 in the experiments. In our paper, Power-SMC (https://arxiv.org/abs/2607.09693) along with other baselines are tested with a candidate budget of N=16 for fair comparison. This explains the difference from the Power-SMC results in [1].
5.Roles of v and z in APS (Q4) It is shown that the effect of sharpening depends on the covariance between correctness and model self-reward. In the proposed APS, vi uses answer agreement as a correctness surrogate, while zi represents standardized differences in sequence log-likelihood. Here, standardization reduces the effect of score-scale differences on the update. Thus gt=Nt1∑i=1Nt(vi−vˉt)zi, updates α through its sign. Removing either v or z therefore prevents APS from updating α.
6.Ablation of APS's adaptation (Q5) We compare APS with two controls to evaluate the contribution of α adaptation with Qwen2.5-Math-7B on MATH500, using the same experiment setup in the paper. They are: PS-voting: Generate 12 parallel responses at α=4 and select the final answer by voting; Static multiple exponents-voting: Generate 4 response at each α∈{2,4,8} and vote ove all 12 responses.
APS improves Pass@1 by 4.2 and 3.2 percentage points over PS-voting and Static multiple exponents-voting, respectively. PS-voting commits all 12 responses to one α, while static multiple exponents-voting allocates four responses to each preset α regardless of the query. APS uses early samples to adapt α to each query and then allocates the remaining budget at the selected exponent. Only responses at the selected exponent enter the final vote. By adapting to each query, APS outperforms fixed-exponent voting and static mixing within the same response budget.