Imagen de Portada

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ning, Yansong, Liu, Mianpeng, Ye, Jingwen, Zhang, Weidong, Liu, Hao
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents
por: Lai, Siqi, et al.
Publicado: (2025)

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

MixReasoning: Switching Modes to Think
por: Lu, Haiquan, et al.
Publicado: (2025)

Strategy-Aware Optimization Modeling with Reasoning LLMs
por: Zhao, Ruiqing, et al.
Publicado: (2026)

UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
por: Ning, Yansong, et al.
Publicado: (2024)

OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
por: Zhang, Shengjia, et al.
Publicado: (2025)

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
por: Wang, Shouren, et al.
Publicado: (2025)

AgentBalance: Backbone-then-Topology Design for Cost-Effective Multi-Agent Systems under Budget Constraints
por: Cai, Shuowei, et al.
Publicado: (2025)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
por: Shi, Dachuan, et al.
Publicado: (2025)

Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data
por: Liu, Xiao, et al.
Publicado: (2024)

MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
por: Zeng, Zhongshen, et al.
Publicado: (2024)

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning
por: Ning, Yansong, et al.
Publicado: (2025)

Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning
por: He, Yang, et al.
Publicado: (2025)

Agent-Omit: Adaptive Context Omission for Efficient LLM Agents
por: Ning, Yansong, et al.
Publicado: (2026)

Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning
por: Zhang, Yujian, et al.
Publicado: (2025)

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs
por: Qi, Shihao, et al.
Publicado: (2025)

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
por: Gan, Siyuan, et al.
Publicado: (2026)

Benchmarking MLLM-based Web Understanding: Reasoning, Robustness and Safety
por: Liu, Junliang, et al.
Publicado: (2025)

TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control
por: Lai, Siqi, et al.
Publicado: (2026)

The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
por: Tan, Yuqiao, et al.
Publicado: (2025)

An Empirical Study of Reasoning Steps in Thinking Code LLMs
por: Xue, Haoran, et al.
Publicado: (2025)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
por: Chen, Haoyang, et al.
Publicado: (2026)

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
por: Yang, Dayu, et al.
Publicado: (2025)

Understanding Mode Switching in Human-AI Collaboration: Behavioral Insights and Predictive Modeling
por: Nargund, Avinash Ajit, et al.
Publicado: (2025)

Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables
por: Zhou, Yitong, et al.
Publicado: (2025)

AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data
por: Alshaikh, Rana, et al.
Publicado: (2025)

Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
por: Liu, Yongjiang, et al.
Publicado: (2025)

Understanding Financial Reasoning in AI: A Multimodal Benchmark and Error Learning Approach
por: Deng, Shuangyan, et al.
Publicado: (2025)

Understanding the Role of LLMs in Multimodal Evaluation Benchmarks
por: Jiang, Botian, et al.
Publicado: (2024)

Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
por: Liu, Jinkun, et al.
Publicado: (2026)

MMLU-Reason: Benchmarking Multi-Task Multi-modal Language Understanding and Reasoning
por: Tie, Guiyao, et al.
Publicado: (2025)

Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs
por: Zhou, Yitong, et al.
Publicado: (2025)

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
por: Shen, Yi, et al.
Publicado: (2025)

DeepThink3D: Enhancing Large Language Models with Programmatic Reasoning in Complex 3D Situated Reasoning Tasks
por: Song, Jiayi, et al.
Publicado: (2025)

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
por: Xu, Zhao, et al.
Publicado: (2024)

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
por: Wang, Shaobo, et al.
Publicado: (2025)

Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
por: Wang, Shouren, et al.
Publicado: (2026)

Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
por: Cao, Jie, et al.
Publicado: (2026)

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
por: Zhang, Zhen, et al.
Publicado: (2025)

Reverse Thinking Makes LLMs Stronger Reasoners
por: Chen, Justin Chih-Yao, et al.
Publicado: (2024)