- Rating
- 1
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper investigates why Tree-of-Thoughts (ToT), despite incorporating explicit step-wise self-evaluation, frequently underperforms Self-Consistency Chain-of-Thought (SC-CoT) on mathematical reasoning tasks. The authors analyze the two paradigms from theoretical and empirical perspectives, emphasizing the role of answer concentration in SC-CoT and candidate coverage and evaluation distributions in ToT. Their theoretical analysis characterizes the conditions under which SC-CoT benefits from additional sampling and ToT successfully preserves correct intermediate reasoning steps.
Based on these analyses, the paper introduces Entropy-Guided Adaptive Reasoning Tree (EGART), a variant of ToT that adaptively determines the number of intermediate reasoning branches to preserve using the entropy of self-evaluation signals. The authors further investigate different evaluation and selection strategies, including voting, independent scoring, stochastic sampling, and top-k selection.
Experiments are conducted using Qwen2.5-3B-Instruct and Qwen2.5-7B-Instruct on GSM8K, MATH, AIME24, and AIME25. The results suggest that evaluation-derived signals, particularly ranking and entropy, can help characterize reasoning behavior and guide adaptive branch preservation. EGART achieves performance comparable to conventional ToT while preserving fewer intermediate reasoning paths in some settings. However, its improvements are generally modest and inconsistent, and SC-CoT remains substantially stronger on most evaluated mathematical reasoning benchmarks.
Critical strengths
-
Useful empirical characterization of SC-CoT and ToT. The paper investigates a relevant discrepancy between sampling-based and search-based reasoning: despite explicitly evaluating intermediate thoughts, ToT often underperforms SC-CoT on mathematical reasoning tasks. The analyses of answer concentration, candidate coverage, and self-evaluation behavior provide useful insights into the practical limitations of these paradigms. In particular, the observation that self-evaluation rankings may retain useful information even when fine-grained evaluation scores are unreliable is informative. These analytical findings are arguably more compelling than the proposed EGART method itself.
-
An intuitive adaptive branch-preservation mechanism with improved theoretical formulation. EGART uses evaluation entropy to dynamically adjust the number of preserved intermediate reasoning branches. The mechanism is straightforward and relatively easy to implement. Compared with the earlier formulation, the theoretical analysis now more explicitly distinguishes the population-level answer distribution in SC-CoT from empirical sampling outcomes, and characterizes ToT selection through a conditional single-step analysis. These revisions improve the mathematical clarity of the paper, although the theoretical justification for EGART itself remains incomplete.
Critical weaknesses
-
Limited methodological novelty and practical improvement. EGART remains fundamentally an adaptive-width variant of ToT, where the preservation budget is controlled by evaluation entropy. Although the paper provides theoretical and empirical motivation for this design, the mechanism does not appear substantially different from existing adaptive beam-width or confidence-based pruning approaches. The experimental evidence does not convincingly establish that evaluation entropy provides a meaningful advantage over simpler adaptive search strategies. Moreover, the improvements over conventional ToT remain modest and inconsistent, while SC-CoT continues to substantially outperform ToT-based approaches on most mathematical reasoning benchmarks. Consequently, the practical significance of the proposed method remains limited.
-
Limitations in the theoretical analysis and its connection to EGART. Although the revised theoretical formulation addresses some previously identified mathematical issues, several limitations remain. First, Theorem 2.2 characterizes SC-CoT through the population-level probability margin between the correct answer and the most probable incorrect answer. However, the empirical analysis primarily uses the number of unique sampled answers as a diversity measure, which is not equivalent to the probability margin appearing in the theorem. Consequently, the relationship between the theoretical characterization and empirical observations remains indirect. Second, Theorem 2.4 assumes that the candidate pool already contains at least one correct intermediate thought and characterizes the probability of preserving a correct candidate in a single reasoning step. This conditional result does not capture generation-stage failures, where no correct candidate is produced, nor does it establish end-to-end reasoning guarantees for the full search tree. More importantly, neither theorem directly establishes that evaluation entropy is an appropriate estimator of the required preservation budget or that the proposed mapping from entropy to search width is theoretically optimal. Low evaluation entropy may also arise when the evaluator confidently favors an incorrect intermediate thought, potentially causing EGART to prune valid reasoning paths. Therefore, the theoretical analysis provides useful intuition for candidate coverage and evaluation behavior, but does not sufficiently justify the central entropy-guided mechanism.
-
Insufficient experimental coverage and statistical evidence. The evaluation remains restricted to Qwen2.5-3B-Instruct and Qwen2.5-7B-Instruct, two relatively small models from the same family. This limits the generalizability of conclusions regarding LLM self-evaluation and reasoning behavior. The benchmark selection also remains problematic: GSM8K and MATH are relatively manageable under repeated sampling, whereas AIME24 and AIME25 are considerably more challenging for models of this scale and each contain only 30 problems. Although the revised manuscript includes additional experimental configurations and reports averages and standard deviations across two seeds, these changes do not fully resolve the statistical limitations. Several reported AIME differences correspond to only one or two correctly solved problems. Furthermore, the primary preservation-budget metric does not directly represent total inference computation, making the practical efficiency advantage of EGART difficult to establish without more comprehensive compute-matched comparisons.
Questions for authors
-
Novelty and comparison with adaptive-width methods. EGART appears to be an adaptive-width implementation of ToT, with evaluation entropy serving as the control signal for branch preservation. Beyond using a different uncertainty metric, what is the key methodological distinction between EGART and existing adaptive beam-width or confidence-based pruning approaches? Can the authors provide a controlled comparison against a simpler adaptive-width ToT baseline under comparable computational budgets?
-
Theoretical justification of entropy-guided preservation. Theorem 2.4 characterizes the probability of preserving a correct intermediate thought in terms of the evaluation margin and preservation budget, under the assumption that the candidate pool contains at least one correct thought. However, EGART determines the preservation budget using evaluation entropy, and the theoretical analysis does not explicitly establish a relationship between entropy and the evaluation margin. Can the authors provide a theoretical justification for the proposed entropy-to-width mapping, or demonstrate that it provides a more reliable preservation strategy than alternative uncertainty measures? In particular, how does the proposed mechanism behave when the evaluator confidently assigns high scores to incorrect thoughts, resulting in low entropy despite the presence of potentially correct alternatives?
-
Relationship between theoretical assumptions and empirical evaluation. Theorem 2.2 characterizes SC-CoT through the probability margin between the correct answer and the most probable incorrect answer, while the empirical analysis primarily considers the number of unique sampled answers. Can the authors clarify how this empirical diversity measure validates the theoretical result? Additionally, given that Theorem 2.4 conditions on the presence of at least one correct candidate, can the authors provide empirical evidence separating failures caused by incorrect candidate generation from failures caused by evaluation-based pruning? Such an analysis would help establish whether EGART addresses the dominant source of error in ToT.
-
Robustness and generalizability. The experiments continue to rely exclusively on Qwen2.5-3B/7B, and the improvements on AIME24/25 remain difficult to interpret because of their small test-set sizes. Can the authors provide additional evidence of robustness, such as evaluations across more seeds, confidence intervals, or experiments involving another model family or larger model? In particular, are the reported improvements over ToT statistically distinguishable from evaluation variance?
-
Actual computational efficiency. The paper emphasizes that EGART can preserve fewer intermediate reasoning paths while maintaining comparable accuracy. However, reducing the number of preserved paths does not necessarily translate into lower overall inference cost, given the additional self-evaluation operations. Although the appendix provides runtime and token-consumption analyses, can the authors establish the benefits of EGART using accuracy-versus-total-compute comparisons against fixed-width ToT and SC-CoT?
12 comments
Response to Weakness 1 & Question 1. Concern about Novelty of EGART and Limited Improvement.
Response: We appreciate your positive attitudes towards our theoretical and empirical analyses. For your concerns, we think you might have a misunderstanding of our paper. To address your concerns, we first summarize your concerns as follows:
- [Similar to Existing Methods] The main idea of EGART is equivalent to existing adaptive beam-width and confidence-based pruning;
- [Limited Improvements on Performance] The reported results show limited improvements compared to ToT;
- [Comparison to Other Methods] Lack comparison with existing adaptive ToT methods for difference.
For the concern 1 & 2, please check our clarification above.
About Comparison with Existing Methods
For the concern 3, we here consider a confidence-based pruning strategy, DeepConf [1]. There are two main differences between DeepConf and our intervention tool, EGART.
- DeepConf is designed for sampling-based reasoning paradigms, such as CoT-SC, while our intervention tool, EGART, is designed for search-based reasoning paradigms;
- From the perspective of thought evaluation, DeepConf evaluates thoughts via a confidence derived from log-probabilities, while EGART adopts the subjective evaluations of LLMs.
- From the perspective of selection strategy, DeepConf preserves the branches by ranking all intermediate thoughts with confidence and taking the top 10%. However, EGART selects intermediate thoughts based on the entropy of evaluation results. In such a case, the preservation budget is manually set in DeepConf, while adaptively determined by evaluation entropy.
To address your concern, we apply the pruning strategy in DeepConf in both ToT and EGART. In this way, on the one hand, we can compare the two self-evaluation strategies; on the other hand, we can further validate the effectiveness of entropy-guided adaptive selection strategy.
Specifically, we first have LLMs generate intermediate thoughts and calculate the confidence with bottom 10% Group Confidence and top-k=20. Then, we preserve branches for ToT with fixed width and for EGART with adaptive width. Results are reported in the following tables (with ). According to the table,
- [Quantitative Results.] In the Qwen2.5-3B case, DeepConf achieves inferior performance to ToT and EGART on simple tasks (e.g., GSM8K and MATH), while comparable or even better performance on hard tasks (e.g., AIME tasks). In the Qwen2.5-7B case, although DeepConf achieves better performance on GSM8K, it underperforms ToT and EGART on other tasks.
- [Resource Consumption.] Meanwhile, since DeepConf merely relies on log-probabilities of LLMs for pruning and only preserves top 10% branches, fewer tokens are consumed.
Qwen2.5-3B
| Methods | GSM8K Acc. (%) ↑ | GSM8K kTok ↓ | MATH Acc. (%) ↑ | MATH kTok ↓ | AIME 24 Acc. (%) ↑ | AIME 24 kTok ↓ | AIME 25 Acc. (%) ↑ | AIME 25 kTok ↓ |
|---|---|---|---|---|---|---|---|---|
| ToT Vote TopK | 88.7±0.1 | 64.26 | 60.1±1.5 | 101.15 | 8.4±2.3 | 144.24 | 1.7±2.3 | 151.10 |
| ToT Score TopK | 89.1±0.2 | 129.66 | 59.5±0.1 | 185.22 | 8.4±2.3 | 249.77 | 5.0±2.4 | 259.77 |
| EGART Vote TopK | 88.1±0.1 | 64.36 | 58.2±1.1 | 106.36 | 8.4±2.3 | 152.78 | 1.7±2.3 | 158.64 |
| EGART Score TopK | 87.2±0.2 | 117.23 | 58.0±0.7 | 158.37 | 6.7±0.0 | 197.24 | 1.7±2.3 | 208.59 |
| DeepConf-ToT | 78.0±1.6 | 18.78 | 51.1±1.1 | 28.31 | 5.0±2.4 | 40.01 | 3.3±0.0 | 40.67 |
| DeepConf EGART | 78.4±0.4 | 25.66 | 52.8±0.4 | 38.51 | 10.0±4.7 | 54.48 | 5.0±2.4 | 55.25 |
Qwen2.5-7B
| Methods | GSM8K Acc. (%) ↑ | GSM8K kTok ↓ | MATH Acc. (%) ↑ | MATH kTok ↓ | AIME 24 Acc. (%) ↑ | AIME 24 kTok ↓ | AIME 25 Acc. (%) ↑ | AIME 25 kTok ↓ |
|---|---|---|---|---|---|---|---|---|
| ToT Vote TopK | 82.9±0.1 | 46.05 | 58.8±0.6 | 66.52 | 11.7±2.3 | 98.96 | 3.4±4.7 | 102.15 |
| ToT Score TopK | 80.5±0.3 | 98.96 | 60.0±0.1 | 125.08 | 16.7±4.7 | 170.17 | 8.4±2.3 | 183.05 |
| EGART Vote TopK | 80.9±1.7 | 38.93 | 58.2±0.5 | 56.55 | 11.7±2.3 | 88.44 | 6.7±0.0 | 89.99 |
| EGART Score TopK | 81.2±0.2 | 96.27 | 58.0±0.1 | 118.03 | 13.3±0.0 | 138.93 | 5.0±2.4 | 156.97 |
| DeepConf-ToT | 81.9±0.0 | 15.28 | 54.9±0.6 | 20.96 | 6.7±4.7 | 30.43 | 3.3±0.0 | 33.63 |
| DeepConf EGART | 83.0±0.5 | 20.10 | 57.5±0.1 | 27.86 | 8.3±2.4 | 41.19 | 6.7±0.0 | 44.18 |
[1] Fu et al., Deep Think with Confidence. ICLR 2026
Response to Weakness 3 & Question 1. Experiments with Matched Computational Budget
Response: According your comments in Question 1, you suggested us to perform tasks with the similar token budget. We agree that token consumption is an important consideration in LLM reasoning. We first explain why more tokens are consumed in ToT.
- Compared to sampling-based paradigms, which directly performs generation, search-based paradigms involves both generation and explicit evaluation phases. Thus, the more tokens are mainly consumed on explicit evaluations.
- Different strategies also consumes different amounts of tokens. For example, in voting, we directly feed all candidates into LLMs for evaluation, while, in scoring, we have to feed candidates one by one for evaluations. The repeated instruction prompts and answer outputs further result in more tokens.
To compare different strategies under the same token budget, we should carefully control the budget of generation, in case that more tokens are consumed in evaluation. Thus, for simplicity, we propose to conduct experiments to compare DeepConf-ToT and DeepConf-EGART. In such a case, since intermediate thoughts are evaluated and selected via confidence-based scores, the consumption of evaluations is zero. We can then evaluate the capabilities of the two selection strategies.
According to the results in the table below, we can observe that DeepConf-ToT fails to outperform DeepConf-EGART in almost all cases, even with the comparable computational budgets. These results demonstrate the advantage of EGART to those simple strategies.
Hope these results can help address your concerns.
Qwen2.5-3B
| Methods | GSM8K Acc. (%) ↑ | GSM8K kTok ↓ | MATH Acc. (%) ↑ | MATH kTok ↓ | AIME 24 Acc. (%) ↑ | AIME 24 kTok ↓ | AIME 25 Acc. (%) ↑ | AIME 25 kTok ↓ |
|---|---|---|---|---|---|---|---|---|
| DeepConf-ToT | 78.0±1.6 | 18.78 | 51.1±1.1 | 28.31 | 5.0±2.4 | 40.01 | 3.3±0.0 | 40.67 |
| DeepConf-ToT (Budget-Matched) | 78.5±1.1 | 24.92 | 51.2±0.9 | 38.21 | 8.3±2.4 | 53.76 | 6.7±0.0 | 54.88 |
| DeepConf EGART | 78.4±0.4 | 25.66 | 52.8±0.4 | 38.51 | 10.0±4.7 | 54.48 | 5.0±2.4 | 55.25 |
Qwen2.5-7B
| Methods | GSM8K Acc. (%) ↑ | GSM8K kTok ↓ | MATH Acc. (%) ↑ | MATH kTok ↓ | AIME 24 Acc. (%) ↑ | AIME 24 kTok ↓ | AIME 25 Acc. (%) ↑ | AIME 25 kTok ↓ |
|---|---|---|---|---|---|---|---|---|
| DeepConf-ToT | 81.9±0.0 | 15.28 | 54.9±0.6 | 20.96 | 6.7±4.7 | 30.43 | 3.3±0.0 | 33.63 |
| DeepConf-ToT (Budget-Matched) | 83.0±1.1 | 19.91 | 56.9±1.5 | 27.82 | 6.7±0.0 | 41.42 | 1.7±2.4 | 44.10 |
| DeepConf EGART | 83.0±0.5 | 20.10 | 57.5±0.1 | 27.86 | 8.3±2.4 | 41.19 | 6.7±0.0 | 44.18 |
A Clarification regarding the Position of Our Paper
We would like to first clarify that, in our paper, EGART is a probing tool, instead of a method for SoTA performance, to validate the efficacy of ranking information and evaluation entropy signals.