arXiv AI November 5, 2026 By Shengjie Wang, Mohsen Fayyaz, Nanyun Peng

Routes of Reasoning: Reading and Reshaping Test-Time Compute in MoE Models

The paper introduces a method to control reasoning behaviors in Mixture-of-Experts (MoE) language models by labeling sentence-level segments with six distinct reasoning behaviors (planning, execution, restatement, fact, reflection, and conclusion). Linear probes on MoE router logits can predict these behaviors nearly as accurately as probes on the full hidden state, enabling the authors to edit router scores during inference to reduce overthinking. This intervention cuts generated tokens by a median of 30.4% (up to 63.3%) across multiple models and benchmarks without significant loss in accuracy, and often improves it.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

benchmarks

arXiv AI

Sep 30

MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller

arXiv:2609.37304v1 Announce Type: new Abstract: Large reasoning models improve performance on challenging problems by allocating additional computation before answering, but longer reasoning does not...

By Zhibin Wen, Tao Han, Lei Bai, Can Li, Yang Xu

llms reinforcement-learning benchmarks

arXiv Machine Learning

Aug 11

Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond

arXiv:2510. 19990v2 Announce Type: replace Abstract: The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving.

By Zachary Horvitz, Raghav Singhal, Hao Zou, Carles Domingo-Enrich, Zhou Yu, Rajesh Ranganath, Kathleen McKeown

llms diffusion reinforcement-learning fine-tuning

Hugging Face Trending Papers

Aug 18

Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

The paper introduces a two‑level internal readout for mixture‑of‑experts reasoning models. First, it compresses the model’s reasoning states into a 64‑axis semantic frame (J64) that reveals process states not captured by the emitted trace, improving held‑out AUC by 0.096–0.135. Second, it reconstructs this frame from native expert‑routing statistics (R64), achieving high correlation with J64 and preserving most of its predictive gain while enabling low‑overhead, test‑time decision making and improved routing policies.

llms

arXiv AI

Jul 14

Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

arXiv:2607. 11266v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps.

By Daeyeop Lee, Hwanjo Yu

llms efficiency benchmarks

arXiv AI

Aug 19

Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

The paper introduces a two‑level readout for mixture‑of‑experts reasoning models. First, it compresses the model’s internal reasoning states into a 64‑dimensional semantic frame (J64) that reveals process dynamics beyond the emitted trace. Second, it reconstructs this frame from native expert‑routing statistics (R64), achieving high correlation and preserving most predictive gains while enabling low‑overhead, test‑time decision making.

By Kang Chen, Sihan Zhao, Yixin Cao, Yugang Jiang

llms

arXiv AI

Jun 11

Forecasting Future Behavior as a Learning Task

arXiv:2606. 11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs.

By Mosh Levy, Yoav Goldberg, Asa Cooper Stickland

llms fine-tuning

One email a morning, machine-written

Related stories

MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller

Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond

Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

Forecasting Future Behavior as a Learning Task