MoE 路由成为控制推理行为的接口，无需训练即可缓解过度思考
Routes of Reasoning: Reading and Reshaping Test-Time Compute in MoE Models
用 MoE 路由器直接关掉'过度思考'，token 省三成还不掉准确率，做推理成本优化的可以看看这篇论文的做法。
研究将推理轨迹切分为句子级片段，标注为规划、执行、复述、事实、反思、结论六种行为，发现 MoE 路由器 logits 上的线性探针用约一半特征数就能达到与残差流探针相当的预测效果。这些信号在覆盖数学、代码、科学、知识、常识的六个数据集间可迁移。在推理时选择性编辑专家路由分数，跨 4 个模型、4 个基准，生成 token 数中位数减少 30.4%，最高 63.3%，准确率下降不超过 0.5 个百分点且常有所提升。
Routes of Reasoning: Reading and Reshaping Test-Time Compute in MoE Models
Reasoning models allocate test-time compute across distinct behaviors such as planning, deriving, and verifying. However, models frequently "overthink," continuing to verify and re-derive long after finding a correct answer. This wastes expensive compute and can even degrade performance. Existing interventions, such as token budgets or steering, primarily regulate reasoning duration rather than targeting specific behaviors. In this work, we demonstrate that Mixture-of-Experts (MoE) routers provide a natural, training-free interface for behavioral control. We first split reasoning traces into sentence-level segments and label each with one of six reasoning behaviors (planning, execution, restatement, fact, reflection, and conclusion), so that every token carries the behavior of its segment. Linear probes on router logits predict this label nearly as well as probes on the residual stream, the model's full hidden state and the standard target for probing, while using about half as many features. These signals generalize: experts associated with a reasoning behavior on one dataset predict the same behavior on the others, across six datasets spanning five domains (math, code, science, knowledge, and commonsense). Building on this, we selectively edit expert router scores during inference to curb overthinking. Across four models and four benchmarks, this intervention reduces the number of generated tokens by a median of 30.4% (and up to 63.3%). Crucially, it encourages the model to stop once the problem is solved, rather than skipping essential reasoning steps. Accuracy never drops by more than 0.5 percentage points, and frequently improves. Ultimately, MoE routing offers both an interpretable lens into reasoning states and a lightweight mechanism for optimizing test-time compute.
