- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces HintMR, a framework that improves mathematical reasoning in small language models through context-aware hints generated by a separate language model at each reasoning step. The authors further propose AdaHintMR, which selectively requests hints based on the solver's token-level Shannon Entropy to reduce inference costs. Experiments across six mathematical reasoning benchmarks and three small language models demonstrate improvements over independent reasoning and several hint-based baselines. AdaHintMR further reduces frontier-model API costs while generally maintaining competitive reasoning accuracy.
Critical strengths
-
Effective intermediate guidance. HintMR provides context-aware hints based on the solver's reasoning history, improving mathematical reasoning accuracy across multiple benchmarks and small language models.
-
Improved inference efficiency. AdaHintMR selectively invokes the hinter, reducing frontier-model API costs while generally maintaining competitive accuracy.
-
Broad empirical evaluation. The experiments cover six mathematical benchmarks, three SLM solvers, and both frontier and local hinters, demonstrating the applicability of the framework across different model configurations.
Critical weaknesses
-
Limited novelty. The central idea of improving reasoning through intermediate hints has been explored in prior work, including HSP, TMATH, ConciseHint and Step Guided Reasoning. HintMR mainly combines context-aware hint generation with stepwise reasoning, while AdaHintMR adopts entropy-based triggering, a commonly used uncertainty estimation technique in existing methods. The methodological novelty over these approaches remains limited.
-
Limited evaluation on smaller models. Although the paper focuses on SLMs, the evaluated solvers are relatively capable models ranging from 3.8B to 9B parameters. Experiments on smaller models (e.g., 0.5B–3B) are needed to assess whether the proposed framework remains effective for more resource-constrained SLMs.
-
Incomplete computational efficiency evaluation. The efficiency analysis mainly considers frontier-model API costs, without accounting for the computational overhead and latency of repeated solver and hinter interactions. This makes it difficult to assess the overall efficiency of the proposed framework.
-
Lack of hint quality analysis. The framework relies on model-generated hints, but the paper provides limited analysis of their correctness and usefulness. Incorrect or misleading hints may propagate errors through subsequent reasoning steps, particularly when using weaker local hinters.
Questions for authors
-
Smaller models. Could the authors extend the evaluation to smaller models (e.g., 0.5B–3B) to demonstrate the effectiveness of HintMR in more resource-constrained settings?
-
Computational efficiency. Could the authors provide a more comprehensive efficiency analysis, including total inference cost and latency for both the solver and hinter?
-
Hint quality. How does the quality of generated hints affect reasoning performance? Could the authors analyze the frequency and impact of incorrect or misleading hints, particularly when using weaker local hinters?
5 comments
Q2: Does HintMR also improve smaller, more resource-constrained solvers in the 0.5B–3B range?
A2: To evaluate the effectiveness of HintMR on smaller solvers, we conducted additional experiments using Qwen3.5-2B with GPT-5.4 as the hinter, following the same reasoning protocol as our main experiments. Table 2 presents the results across five mathematical reasoning benchmarks.
Table 2: Accuracy (%) of Qwen3.5-2B with GPT-5.4 as the Hinter
| Method | AIME-24 | AIME-25 | AIME-26 | AMC23 | MATH-500 |
|---|---|---|---|---|---|
| No Hint | 20.00 | 16.67 | 13.33 | 52.50 | 75.00 |
| HintMR | 30.00 | 20.00 | 20.00 | 57.50 | 82.00 |
| AdaHintMR | 26.67 | 20.00 | 20.00 | 55.00 | 82.00 |
As shown in Table 2, both HintMR and AdaHintMR improve Qwen3.5-2B accuracy across all five benchmarks. For example, HintMR improves AIME-2024 accuracy from 20.00% to 30.00% and MATH-500 accuracy from 75.00% to 82.00%. AdaHintMR also improves upon No Hint, although its accuracy is slightly lower than HintMR on AIME-2024 and AMC23.
Overall, these additional results demonstrate that the benefits of intermediate guidance extend to smaller 2B-parameter solvers. We also observe that larger solvers generally achieve stronger performance with hint-based guidance. For example, on AIME-2024, HintMR achieves 30.00% with Qwen3.5-2B, 80.00% with Phi-4-mini (3.8B), 76.67% with Gemma-2-9B, and 76.67% with Qwen3.5-9B. Similarly, on MATH-500, accuracy reaches 82.00%, 87.80%, 87.60%, and 88.80%, respectively. While performance does not increase strictly with parameter count, these results suggest that larger, more capable solvers can generally utilize intermediate guidance more effectively.
Q3: How efficient is the full framework once solver and hinter computation, repeated calls, and wall-clock latency are included?
A3: We would like to clarify that Table 2 of our original submission reports external GPT-5.4 API costs only, rather than total end-to-end computational costs. Our local experiments were conducted on institutional shared GPUs, which incurred no direct monetary charges. To provide a more comprehensive efficiency analysis, Table 3 reports average solver-generated tokens and wall-clock inference latency for No Hint, HintMR, and AdaHintMR, using Qwen3.5-9B as the solver and GPT-5.4 as the hinter, alongside direct GPT-5.4 API inference.
Table 3: Solver Token Usage and Inference Latency Across Mathematical Reasoning Benchmarks
| Dataset | No Hint Tokens | HintMR Tokens | AdaHintMR Tokens | No Hint Latency (s) | HintMR Latency (s) | AdaHintMR Latency (s) | GPT-5.4 Direct Latency (s) |
|---|---|---|---|---|---|---|---|
| AIME-2024 | 9,203 | 8,642 | 6,343 | 757 | 519 | 339 | 8.8 |
| AIME-2025 | 8,168 | 11,968 | 8,178 | 622 | 697 | 475 | 11.2 |
| AIME-2026 | 6,899 | 11,176 | 8,755 | 578 | 649 | 581 | 11.6 |
| AMC-2023 | 4,622 | 3,983 | 2,783 | 424 | 242 | 146 | 5.5 |
| MATH-500 | 2,648 | 1,956 | 2,016 | 130.7 | 107.4 | 106.5 | 2.5 |
| Minerva-Math | 2,679 | 1,307 | 1,401 | 97.2 | 73.5 | 77.1 | 2.8 |
Token counts represent solver-generated output tokens and exclude hinter input/output tokens. All local experiments used a single NVIDIA A100-SXM4-80GB.
Computational overhead. AdaHintMR generally reduces solver token usage and inference latency compared with standard HintMR. For example, on AIME-2024, solver tokens decrease from 8,642 to 6,343, while latency decreases from 519 to 339 seconds. On AMC-2023, latency decreases from 242 to 146 seconds. Compared with No Hint, AdaHintMR also reduces latency on five of the six benchmarks. However, the improvements are not uniform: on AIME-2026, AdaHintMR uses more solver tokens than No Hint and has slightly higher latency.
Hinter overhead and API efficiency. Repeated hinter calls introduce additional token consumption and latency. AdaHintMR reduces this overhead by selectively requesting hints based on step-level entropy. As reported in Table 2 of our original submission, GPT-5.4 API cost decreases from 1.21¢ to 1.01¢ on AIME-2024, 1.44¢ to 1.04¢ on AIME-2025, and 0.83¢ to 0.32¢ on AMC-2023 compared with HintMR.
Overall, AdaHintMR improves the efficiency of solver–hinter collaboration by reducing external API costs and, on most benchmarks, wall-clock latency compared with HintMR. However, direct GPT-5.4 inference remains substantially faster, as it is accessed through a hosted API, whereas our solver runs locally on a single GPU.
Q4: How do incorrect or misleading hints, especially from weaker local hinters, affect the solver's reasoning accuracy?
A4: To evaluate hint quality, we conducted an additional analysis of hints generated by GPT-5.4 and Qwen3.8-27B, using GPT-6.1-sol as the annotator. Each hint was classified into four categories: (i) correct and useful, (ii) correct but vague, (iii) incorrect or misleading, and (iv) answer leakage. We clarify that the hinter instructions in Appendix B.6 explicitly prohibit revealing final answers or complete solutions, ensuring that the solver remains responsible for deriving the solution. Table 4 summarizes the results.
Table 4: Hint Quality Analysis Across Different Hinter Models (%)
| Hinter | Method | Correct/Useful | Correct but Vague | Incorrect/Misleading | Answer Leakage |
|---|---|---|---|---|---|
| GPT-5.4 | HintMR | 72.0 | 18.5 | 9.5 | 0.0 |
| GPT-5.4 | AdaHintMR | 68.1 | 24.5 | 7.4 | 0.0 |
| Qwen3.8-27B | HintMR | 33.0 | 60.9 | 6.1 | 0.0 |
| Qwen3.8-27B | AdaHintMR | 37.1 | 52.5 | 10.4 | 0.0 |
Percentages are based on GPT-6.1-sol annotations of sampled hints.
Hint quality and reasoning accuracy. GPT-5.4 produces substantially more correct and useful hints (68.1–72.0%) than Qwen3.8-27B (33.0–37.1%). In contrast, the weaker local hinter generates a much larger proportion of correct but vague and incorrect/misleading hints (62.9–67.0% combined), which may provide insufficient guidance or redirect the solver toward incorrect reasoning. This offers a plausible explanation for the lower accuracy observed when Qwen3.5-9B is paired with Qwen3.8-27B as the hinter. Conversely, the substantially higher proportion of correct and useful hints from GPT-5.4 provides more actionable intermediate guidance, consistent with the stronger reasoning accuracy achieved by the same Qwen3.5-9B solver.
These findings align with our original experimental results. On AIME-2024, HintMR achieves 76.67% accuracy with GPT-5.4 as the hinter, compared with 40.00% using Qwen3.8-27B. Similarly, on AIME-2025, AdaHintMR achieves 63.33% with GPT-5.4 versus 30.00% with Qwen3.8-27B. Thus, the observed relationship between hint quality and reasoning accuracy suggests that the effectiveness of solver–hinter collaboration depends strongly on the hinter's ability to provide correct, actionable guidance, although the aggregate annotations do not establish a direct causal relationship. No explicit answer leakage was detected in the annotated samples.
We sincerely thank the reviewer for recognizing the effectiveness of context-aware intermediate guidance in improving mathematical reasoning accuracy, the inference efficiency of AdaHintMR in reducing frontier-model API costs while maintaining competitive accuracy, and the broad empirical evaluation across six mathematical benchmarks, three SLM solvers, and both frontier and local hinters. We also appreciate the reviewer’s concerns regarding novelty, smaller model backbones, end-to-end efficiency, and the potential impact of incorrect hints. We address each concern below.
A1: We acknowledge that hint generation, stepwise reasoning, and uncertainty estimation are established techniques. Our contribution is context-aware solver–hinter collaboration with adaptive hint invocation, rather than the individual components.
(a) Comparison with prior methods. The key differences are summarized below.
Unlike one-time or self-generated guidance, HintMR uses a separate hinter conditioned on the solver's accumulated reasoning, supporting both frontier and local model collaboration.
(b) Novelty of AdaHintMR. AdaHintMR uses step-level token entropy to selectively invoke the hinter, rather than requesting hints at every step. This reduces unnecessary external-model calls and API expenditure without additional training. (c) Empirical evidence. Our original submission already compares against HSP and TMATH (Table 3) and evaluates adaptive variants (Table 1). Table 1 summarizes these results alongside other baselines.
Table 1: Accuracy (%) Comparison with Existing Reasoning Baselines
Results are from Tables 1 and 3 of our original submission. Single GPT-5.4 Hint is an additional baseline.
Overall, our contribution is improving SLM mathematical reasoning through context-aware guidance from a separate hinter, while reducing external API costs through adaptive hint invocation.
[1] Jinlan Fu, Shenzhen Huangfu, Hang Yan, See-Kiong Ng, and Xipeng Qiu. Hint-before solving prompting: Guiding llms to effectively utilize encoded knowledge. arXiv preprint arXiv:2402.14310, 2024.
[2] Changyong Qi, Yuang Wei, Haoxin Xu, Longwei Zheng, Peiji Chen, and Xiaoqing Gu. TMATH: A dataset for evaluating large language models in generating educational hints for math word problems. In Proceedings of the 31st International Conference on Computational Linguistics, pp. 5082–5093, 2025.
[3] Siao Tang, Xinyin Ma, Gongfan Fang, and Xinchao Wang. Concisehint: Boosting efficient reasoning via continuous concise hints during generation. arXiv preprint arXiv:2506.18810, 2025.
[4] Lang Cao, Yingtian Zou, Chao Peng, Renhong Chen, Wu Ning, and Yitong Li. Step guided reasoning: Improving mathematical reasoning using guidance generation and step reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 21112–21129, 2025.