Cover Image

Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Yang, Ding, Xiao, Cai, Bibo, Zhang, Yufei, Xiong, Kai, Sun, Zhouhao, Qin, Bing, Liu, Ting
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation
by: Sun, Zhouhao, et al.
Published: (2024)

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
by: He, Yang, et al.
Published: (2026)

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
by: Zhao, Yang, et al.
Published: (2026)

Large Language Models Are Still Misled by Simple Bias Ensembles
by: Sun, Zhouhao, et al.
Published: (2025)

GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models
by: Sun, Zhouhao, et al.
Published: (2026)

Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning
by: Zhao, Yang, et al.
Published: (2024)

ExpeTrans: LLMs Are Experiential Transfer Learners
by: Gao, Jinglong, et al.
Published: (2025)

UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
by: Zhao, Yang, et al.
Published: (2025)

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
by: Zhao, Yang, et al.
Published: (2026)

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
by: Xiong, Kai, et al.
Published: (2023)

Causal-Guided Active Learning for Debiasing Large Language Models
by: Du, Li, et al.
Published: (2024)

Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models
by: Sun, Zhouhao, et al.
Published: (2025)

Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
by: Xiong, Kai, et al.
Published: (2024)

Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection
by: Zhao, Yang, et al.
Published: (2025)

Com$^2$: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models
by: Xiong, Kai, et al.
Published: (2025)

Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns
by: Zhao, Yang, et al.
Published: (2024)

ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
by: Xiong, Kai, et al.
Published: (2022)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
by: Zhang, Xiaoyun, et al.
Published: (2025)

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
by: Xiong, Kai, et al.
Published: (2024)

RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning
by: Liu, Yuhang, et al.
Published: (2026)

CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer
by: Gao, Jinglong, et al.
Published: (2025)

MixReasoning: Switching Modes to Think
by: Lu, Haiquan, et al.
Published: (2025)

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
by: Zhao, Weixiang, et al.
Published: (2025)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
by: Du, Yanrui, et al.
Published: (2026)

Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
by: Pan, Zhihong, et al.
Published: (2025)

Self-Evolving GPT: A Lifelong Autonomous Experiential Learner
by: Gao, Jinglong, et al.
Published: (2024)

Text Difficulty Study: Do machines behave the same as humans regarding text difficulty?
by: Chen, Bowen, et al.
Published: (2022)

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
by: Chen, Haolin, et al.
Published: (2024)

Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion
by: Gao, Jinglong, et al.
Published: (2024)

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
by: Lu, Xin, et al.
Published: (2025)

INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling
by: Shi, Haochen, et al.
Published: (2025)

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
by: Feng, Guhao, et al.
Published: (2024)

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
by: Lee, Sangmook, et al.
Published: (2025)

Are Your LLMs Capable of Stable Reasoning?
by: Liu, Junnan, et al.
Published: (2024)

Efficient Reasoning via Chain of Unconscious Thought
by: Gong, Ruihan, et al.
Published: (2025)

MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression
by: Sun, Libo, et al.
Published: (2026)

SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model
by: Zhang, Wencheng, et al.
Published: (2025)

ARS: Automatic Routing Solver with Large Language Models
by: Li, Kai, et al.
Published: (2025)

Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge
by: Zhang, Wenbo, et al.
Published: (2026)

AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints
by: Zeng, Yirong, et al.
Published: (2026)