arXiv Machine Learning October 23, 2026 By Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang

When Should LLMs Reason? Adaptive Inference Routing via Entropy Dynamics

Read the original on arXiv Machine Learning →

The paper introduces EDRM, an entropy‑dynamics‑based routing framework that decides whether to use direct, standard, or chain‑of‑thought decoding for large language models. By analyzing early decoding entropy, EDRM identifies tasks that benefit from explicit reasoning and routes queries accordingly, achieving 16–55% token savings while maintaining accuracy across 15 benchmarks and 7 LLMs. The study also shows that a short direct fallback branch can further improve accuracy by up to 4.9 percentage points compared to routing alone.

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 Machine Learning.

arXiv AI

Jun 16

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions

arXiv:2605. 22873v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial?

By Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang

llms benchmarks

arXiv AI

Sep 3

SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology

The paper introduces SCX Router, a lightweight GLiClass-based model selector that assigns suitability scores to inference-time language models without autoregressive generation. It uses a 0.6B-parameter Qwen3 decoder with a shallow bidirectional scorer, preserving a text-only key–value cache across sessions and predicting task attributes such as type, difficulty, and expected output length. The authors build a comprehensive task ontology with 23 families, 115 types, and 1,173 synthetic examples, generating 150,000 verifier-scored tasks to train the router, which outperforms baseline models on LiveBench subsets with a top‑1 score of 0.707 versus 0.696 for the strongest fixed model.

By Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko, Dmytro Vodianytskyi, Oleksandr Lukashov

llms agents benchmarks safety

arXiv AI

Aug 12

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

arXiv:2602. 09924v4 Announce Type: replace-cross Abstract: Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging.

By William Lugoloobi, Thomas Foster, William Bankes, Chris Russell

llms

arXiv Computation and Language

Oct 15

RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing

arXiv:2610.19705v1 Announce Type: new Abstract: LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built arou...

By Xiaohan Wang, Haozhen Zhang, Qingyuan Liu, Tao Feng, Wenya Wang

llms agents

arXiv Computation and Language

Sep 1

Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey

arXiv:2603.04445v3 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent mo...

By Yasmin Moslem, John D. Kelleher

llms reinforcement-learning

arXiv Machine Learning

Sep 1

ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning

arXiv:2608.28771v1 Announce Type: new Abstract: Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with...

By Xin Jiang, Minhao Wang, Wen Wu, Zhentao Xie, Shangheng Du, Jinxin Shi, Jiabao Zhao

llms reinforcement-learning

One email a morning, machine-written

Related stories

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions

SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing

Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey

ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning