- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes DART, a training-free adaptive reasoning algorithm whose core idea is to use answer-token entropy, the mean entropy of token distributions across positions in a generated answer to reflect subproblem difficulty. The method has two parts: first, a difficulty-aware router, after one-time offline calibration, classifies each subproblem into solve directly / decompose directly / entropy-gated regions, keeping the answer when entropy is low and decomposing further when it is high, thereby balancing accuracy and inference cost; second, a confidence-aligned self-critique mechanism in which the critic outputs both a score and the confidence of that score token, jointly constraining them to limit the propagation of intermediate-answer errors. Across three tasks set intersection, sorting, and keyword counting on Qwen3-32B and Llama3.1-70B, DART reduces average error by 22%–57% and online inference cost by 51%–72% relative to the best baseline on each backbone, achieving the lowest error in most configurations at lower cost.
Critical strengths
1.The research problem is clearly defined and the motivation is sound. Deciding at the subproblem level whether to continue decomposition is more fine-grained than allocating a fixed budget to the entire request. The authors also demonstrate the limitations of entropy across different granularities and address these differences through a zone-partitioning strategy.
2.Several results show strong practical improvement. For example, on Qwen's 64-element sorting, the average error drops from the best baseline's 4.56 to 1.43, with clearly reduced cost as well. Results of this kind support the value of the framework on the tested tasks.
3.The ablations and supplementary experiments are fairly complete. The paper includes analyses of fixed decomposition depth, self-correction, confidence constraints, feedback history, random routing, the entropy threshold, and the number of iterations. Appendix C.7 additionally runs direct solving and forced decomposition on the same subproblems, which comes closer to validating whether the routing decision is useful than merely showing entropy–error correlation curves.
Critical weaknesses
1.Task coverage is insufficient and does not yet support a claim of general complex-reasoning contribution. All three tasks have strongly decomposable structures, and their decomposition and aggregation rules are easy to specify explicitly. These tasks are suitable for testing local mechanisms, but they do not adequately demonstrate that the method can handle reasoning tasks in which the decomposition plan itself is uncertain, subproblems are mutually dependent, and answers are hard to verify precisely.
2.Novelty positioning still need strengthening. Regarding related work, DiffAdapt and other several works has already studied entropy, difficulty, and reasoning-strategy selection, Their implementations may differ from DART, but they should be included in a more direct comparison to clarify DART's unique contribution.
Questions for authors
See weaknesses
4 comments
(a) Comparison of mechanisms
| Related method | Main limitations | DART’s corresponding advantages |
|---|---|---|
| DiffAdapt [1] | Requires a trained routing classifier; selects inference configurations for the whole question | No routing-network training; clustering-based calibration selects solving or decomposition per subproblem |
| GlimpRouter [2] | Requires switching between small and large models; lacks explicit recursive decomposition and a separate correction mechanism | Uses a single model; adaptive decomposition and confidence-aligned correction in both solving and aggregation |
| CoFiCot [3] | Requires multiple candidates; main configurations rely on process/outcome reward models | Reuses the initial answer and its entropy; self-critique with the same model, without a dedicated reward model |
The discussion of these methods has been added to Section 2.2 (Related Work) of the manuscript.
DART advances beyond DiffAdapt in two respects:
(1) A closer characterization of the entropy–performance relationship. DiffAdapt [1] uses U-shaped entropy patterns across difficulty levels, multiple response samples, and a trained classifier. DART uses group-level mean error and entropy–error correlation to calibrate capability regions through clustering, directly guiding solving or decomposition without training a routing network.
(2) Adaptive problem structure and correction. DiffAdapt adjusts inference configurations for the whole question without explicitly changing its structure; more reasoning may be insufficient when a problem exceeds the model’s direct-solving capability. DART recursively decomposes problems to reduce subproblem difficulty and applies self-critique during both solving and aggregation.
We further include DiffAdapt in the experiments on all five tasks and both models.
(b) Mathematical and logical reasoning tasks
Reference for changes: DiffAdapt on the same task and model. DART’s accuracy differences are in percentage points (pp), and cost changes are relative percentages.
| Task / Model | DART accuracy (%) | DiffAdapt accuracy (%) | DART cost | DiffAdapt cost |
|---|---|---|---|---|
| DeepMath / Qwen | 80.2 (↑4.7 pp) | 75.5 | 34.78 (↓4.4%) | 36.38 |
| DeepMath / Llama | 62.9 (↑5.8 pp) | 57.1 | 32.81 (↓8.5%) | 35.86 |
| ProverQA / Qwen | 80.3 (↑2.7 pp) | 77.6 | 12.76 (↓18.7%) | 15.70 |
| ProverQA / Llama | 75.2 (↑2.6 pp) | 72.6 | 20.82 (↓8.5%) | 22.76 |
DART improves accuracy by 2.6–5.8 percentage points while reducing cost by 4.4%–18.7% across all four settings.
(c) Structured tasks
Entries report mean final-answer error / total cost over 100 problems.
Reference for changes: DiffAdapt on the same task, input size, and model. Annotations show DART’s error and cost changes.
| Task / Size | Qwen: DART | Qwen: DiffAdapt | Llama: DART | Llama: DiffAdapt |
|---|---|---|---|---|
| Set intersection (N=32) | 0.19 (↓24.0%) / 1.96 (↓8.4%) | 0.25 / 2.14 | 0.03 (↓96.5%) / 2.42 (↓6.2%) | 0.86 / 2.58 |
| Set intersection (N=64) | 1.30 (↓50.8%) / 5.66 (↓11.8%) | 2.64 / 6.42 | 0.83 (↓46.8%) / 8.85 (↓13.2%) | 1.56 / 10.20 |
| Set intersection (N=128) | 7.75 (↓49.6%) / 19.40 (↑4.8%) | 15.39 / 18.52 | 6.43 (↓48.2%) / 27.91 (↑10.8%) | 12.41 / 25.19 |
| Sorting (N=32) | 0.54 (↓10.0%) / 1.07 (↓3.6%) | 0.60 / 1.11 | 1.55 (↓20.9%) / 2.93 (↓17.5%) | 1.96 / 3.55 |
| Sorting (N=64) | 1.43 (↓31.6%) / 5.85 (↓30.9%) | 2.09 / 8.47 | 4.54 (↓19.6%) / 13.06 (↓18.5%) | 5.65 / 16.02 |
| Sorting (N=128) | 5.56 (↓43.9%) / 17.16 (↓14.9%) | 9.91 / 20.17 | 14.90 (↓7.7%) / 35.36 (↓13.2%) | 16.15 / 40.75 |
| Keyword counting | 1.80 (↓12.6%) / 5.42 (↓24.9%) | 2.06 / 7.22 | 1.18 (↓17.5%) / 9.65 (↓20.4%) | 1.43 / 12.12 |
DART achieves lower error in all 14 structured-task settings and lower cost in 12. The two cost exceptions are set intersection at N=128 on both models.
References
[1] Xiang Liu et al. DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference. ICLR 2026.
[2] Wenhao Zeng et al. GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts. Findings of ACL 2026, pp. 17850–17864.
[3] Dongxu Zhang et al. Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement. UAI 2026.
Manuscript changes: Section 2.2 adds the three related methods and clarifies DART’s positioning (p. 3, lines 138–144). Appendix C.3 gives DiffAdapt implementation details (p. 22, lines 1148–1152); Sections 4.1 and 4.2 describe the baseline and comparison (p. 8, lines 415–417; p. 9, lines 438–440). DiffAdapt results appear in Figure 4 (p. 7, lines 357–360), Tables 10–12 (p. 27, lines 1411–1452), and Table 13 (p. 28, lines 1459–1474).
We hope that our responses adequately address the reviewer's concerns. We would be glad to hear any further feedback.
The author's response addressed my concerns, so I will raise my score
Thank you for your constructive feedback and support
Dear Reviewer i3SN,
Thank you for your careful reassessment and for raising your score. We are pleased that our responses and additional experiments have addressed your concerns.
Following your suggestions, we expanded our evaluation to DeepMath and ProverQA, added DiffAdapt comparisons across all five tasks and both models, and clarified DART’s contributions relative to other entropy-driven adaptive methods. These results and discussions have been incorporated into the revised manuscript.
We sincerely appreciate your time and constructive feedback, which helped us strengthen the empirical evaluation and clarify the positioning of our work.
Best regards,
The Authors
Thank you for your careful and thorough review of our work. We add broader reasoning tasks and direct comparisons with DiffAdapt, with the evidence below.
[W1: Evaluation beyond Predefined Structural Decomposition]
Thank you for your suggestion. We have added two benchmarks: DeepMath [1] and ProverQA [2]. DeepMath requires models to plan mathematical derivations and build on intermediate results; ProverQA requires multistep logical reasoning in which later inferences depend on earlier conclusions. Both involve choosing decomposition steps and reasoning with dependencies between subproblems.
Reference for changes: DART versus the baseline with the highest accuracy in each column (CR, GoT, GoT, and CR, from left to right). Accuracy differences are in percentage points (pp); cost changes use the same baseline in each column.
Entries report final-answer accuracy (%) / reported total cost on each evaluation set.
Underlining marks the baseline with the highest accuracy in each column.
DART achieves the highest accuracy in all four task–model settings, at lower cost than the most accurate baseline in each. These results extend the evidence from fixed structural decomposition to mathematical and multistep logical reasoning with model-generated decomposition steps.
References
[1] Zhiwei He et al. DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning. ICLR 2026.
[2] Chengwen Qi et al. Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation. ICLR 2025.
Manuscript changes: Sections 3.2 and 3.4 and Algorithm 1 clarify unified grouping and probe reuse (pp. 5–6, lines 238–294 and 318–324). Section 4.1 gives the datasets and sample sizes (pp. 7–8, lines 375–378 and 402–404); Figure 4 (p. 7, lines 357–360), Section 4.2 (p. 9, lines 448–450), and Appendix C.5, Table 13 (p. 28, lines 1459–1474), report the results. Task grouping is documented in Appendix C.2 (p. 19, lines 999–1007; Table 8, p. 20, lines 1027–1050) and Appendix C.4 (p. 22, lines 1160–1171; Figures 17–20, p. 26).
[W2: Comparison with Entropy-Driven Adaptive Methods and Contribution Positioning]
Thank you for your suggestion. DART characterizes the relationship between answer-token entropy and solving performance across difficulty levels. Through clustering-based calibration, it enables subproblem-level adaptive decomposition and confidence-aligned correction within a single model, without training a routing network. The following table compares DART with related methods.