- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper investigates the performance degradation caused by KV-cache compression during long chain-of-thought (Long-CoT) reasoning. The authors identify two major failure modes associated with existing attention-based KV-cache eviction methods: Lost Objective and Commitment Collapse.
To address these issues, the paper proposes CAPE, a training-free method that employs context reconstruction to select and preserve important KV entries from the original question, thereby mitigating objective loss. Meanwhile, it adjusts the Softmax temperature according to the logical sequence length and physical cache size to alleviate the attention entropy deficit induced by KV-cache compression.
Experimental results demonstrate that CAPE generally outperforms existing compression baselines under matched cache budgets, recovering part of the reasoning accuracy lost under compression while substantially reducing KV-cache memory consumption.
Critical strengths
-
Valuable analysis of failure modes. The paper goes beyond final-answer accuracy by identifying and analyzing two failure modes, Lost Objective and Commitment Collapse, providing a more fine-grained understanding of KV-cache compression failures during long-CoT reasoning.
-
Simple and complementary method design. CAPE combines objective preservation with attention temperature adjustment to address different failure modes. Both components are training-free and can be readily integrated into existing dynamic KV-cache compression frameworks.
-
Competitive experimental performance. The experiments cover three reasoning models and three mathematical reasoning benchmarks. CAPE consistently matches or outperforms the evaluated compression baselines under the reported settings.
-
Comprehensive ablation and diagnostic analyses. The paper provides question-recall evaluations, commitment-delay analysis, attention entropy interventions, and component ablation studies, offering useful insights into the effectiveness of the proposed method.Critical Weaknesses.
Critical weaknesses
-
Insufficient direct validation of the entropy-matching mechanism.The temperature scaling derivation relies on assumptions such as i.i.d. and Gaussian attention logits, which may not hold after importance-based KV eviction. Moreover, although temperature scaling improves accuracy, the paper does not directly compare the actual attention entropy of CAPE with that of FullKV. Therefore, the proposed entropy-matching mechanism remains insufficiently validated.
-
Limited methodological novelty. CAPE's temperature scaling and context reconstruction components are closely related to existing methods such as InfoScale, AhaKV, and KVzip. Furthermore, Random Attention (Wang et al., 2026) demonstrates that preserving the original prompt while randomly evicting reasoning tokens can also achieve competitive performance. Although CAPE provides some ablation studies, more comprehensive comparisons with these simpler strategies are needed to clarify the additional value of reconstruction-based anchor selection and the overall combined design.
-
Limitations in measuring Commitment Collapse. The paper defines a trace as answer-ready when the correct answer first appears in the reasoning text, but this does not necessarily indicate that the model has completed its reasoning. Furthermore, counting expressions such as "Wait" and "Let me check" may not reliably distinguish legitimate verification from unnecessary reasoning loops. Additional manual validation or more reliable semantic evaluation would strengthen the analysis.
-
Limited evidence of generalizability. The experiments are restricted to MATH-500 and AIME24/25. It remains unclear whether fixed Objective Anchors are effective for tasks such as code generation, long-document reasoning, and complex instruction following, where multiple constraints or objectives may need to be preserved. Further evaluation is needed to establish the generalizability of the proposed method.
Questions for authors
-
Could the authors directly measure and compare the actual attention entropy of FullKV, standard KV-cache compression methods, and CAPE across different decoding lengths and attention layers to verify whether the proposed temperature scaling achieves the intended entropy matching?
-
How much additional benefit does reconstruction-based Objective Anchor selection provide compared with simply preserving the entire prompt? Could the authors include fair comparisons with simpler approaches such as Random Attention?
-
How reliable is the definition of answer-ready based on the first occurrence of the correct answer in the reasoning text? Have the authors conducted manual inspections to distinguish genuine Commitment Collapse from legitimate subsequent verification?
-
How does CAPE perform on non-mathematical tasks, such as code generation and long-document reasoning? Are fixed Objective Anchors still effective when prompts contain multiple complex constraints?