长链推理的注意力衰减问题终于有了针对性解法，做推理模型优化或长上下文应用的团队值得关注——InsightReplay简单有效，可以直接在现有CoT框架上尝试。
研究发现，思维链推理长度增加时，模型对早期关键洞察的注意力会逐渐减弱，导致准确率在达到峰值后下降。为此，研究者提出InsightReplay方法，让模型在推理过程中定期提取关键洞察并回放到当前生成位置附近，保持其可访问性。在8B和30B规模的Qwen3.5、DeepSeek-R1-Distill-Qwen、Gemma-4模型上，覆盖AIME、HMMT、GPQA Diamond、LiveCodeBench v5等基准测试，3轮InsightReplay在所有24个设置中均带来准确率提升，平均提升1.65个百分点，最高单设置提升达9.2个百分点。结果表明，测试时扩展的有效性不仅取决于推理量，还取决于关键中间洞察在长推理轨迹中的可访问性。
Stateful Reasoning via Insight Replay
Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its benefits do not scale monotonically with chain length: while longer CoT generally enables a model to tackle harder problems, on a given problem, accuracy typically increases with CoT length up to a point, after which it declines. We identify a major cause of this phenomenon: as the CoT grows, the model's attention to critical insights produced earlier in the trace gradually weakens, making those insights progressively less accessible when they are most needed. Therefore, we propose \textbf{InsightReplay}, a stateful reasoning approach in which the model periodically extracts critical insights from its reasoning trace and replays them near the active generation frontier, keeping them accessible as the reasoning scales. Extensive experiments on a $\mathbf{2}\!\times\!\mathbf{3}\!\times\!\mathbf{4}$ benchmark grid, covering model scales $\{\text{8B}, \text{30B}\}$, model families $\{\text{Qwen3.5}, \text{DeepSeek-R1-Distill-Qwen}, \text{Gemma-4}\}$, and reasoning benchmarks $\{\text{AIME}, \text{HMMT}, \text{GPQA Diamond}, \text{LiveCodeBench v5}\}$, show that 3-round InsightReplay yields accuracy gains across \textbf{all 24 settings}, with an averaged improvement of $\mathbf{+1.65}$ points over standard CoT, and a largest single-setting gain of $\mathbf{+9.2}$ points on R1-Distill-32B's LiveCodeBench v5 subset. Our results suggest that the effectiveness of test-time scaling depends not only on how much a model reasons, but also on whether critical intermediate insights remain accessible throughout long reasoning trajectories.