Cover Image

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Weixiang, Sui, Xingyu, Guo, Jiahe, Hu, Yulin, Deng, Yang, Zhao, Yanyan, Zhi, Xuda, Huang, Yongbo, He, Hao, Che, Wanxiang, Liu, Ting, Qin, Bing
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement
by: Zhao, Weixiang, et al.
Published: (2025)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
by: Zhao, Weixiang, et al.
Published: (2025)

When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
by: Guo, Jiahe, et al.
Published: (2026)

Lens: Rethinking Multilingual Enhancement for Large Language Models
by: Zhao, Weixiang, et al.
Published: (2024)

TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
by: Sui, Xingyu, et al.
Published: (2026)

On Safety Risks in Experience-Driven Self-Evolving Agents
by: Zhao, Weixiang, et al.
Published: (2026)

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
by: Zhao, Weixiang, et al.
Published: (2025)

OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
by: Hu, Yulin, et al.
Published: (2026)

Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
by: Zhao, Weixiang, et al.
Published: (2025)

Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
by: Zhao, Weixiang, et al.
Published: (2024)

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
by: Zhao, Weixiang, et al.
Published: (2025)

Large Language Model Agents Are Not Always Faithful Self-Evolvers
by: Zhao, Weixiang, et al.
Published: (2026)

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter
by: Zhao, Weixiang, et al.
Published: (2025)

SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
by: Zhao, Weixiang, et al.
Published: (2024)

Learning to Learn from Multimodal Experience
by: Sui, Xingyu, et al.
Published: (2026)

ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments
by: Zhao, Weixiang, et al.
Published: (2026)

MPO: Multilingual Safety Alignment via Reward Gap Optimization
by: Zhao, Weixiang, et al.
Published: (2025)

Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
by: Chen, Qiguang, et al.
Published: (2024)

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning
by: Chen, Qiguang, et al.
Published: (2025)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
by: Guo, Jiahe, et al.
Published: (2026)

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
by: Jin, Can, et al.
Published: (2026)

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
by: Fu, Xing, et al.
Published: (2026)

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence
by: Zhao, Weixiang, et al.
Published: (2024)

Improving Language Model Reasoning with Self-motivated Learning
by: Feng, Yunlong, et al.
Published: (2024)

Reason-to-Transmit: Deliberative Adaptive Communication for Cooperative Perception
by: Bansal, Aayam, et al.
Published: (2026)

Enhancing Numerical Reasoning with the Guidance of Reliable Reasoning Processes
by: Wang, Dingzirui, 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)

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
by: Wu, Di, et al.
Published: (2026)

Text-Driven Emotionally Continuous Talking Face Generation
by: Yang, Hao, et al.
Published: (2026)

Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks
by: Guan, Jiannan, et al.
Published: (2025)

Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond
by: Wang, Dingzirui, et al.
Published: (2025)

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

Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
by: Wang, Chaojie, et al.
Published: (2024)

Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
by: Li, Ziheng, et al.
Published: (2025)

Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format
by: Wang, Dingzirui, et al.
Published: (2025)

A Survey of Table Reasoning with Large Language Models
by: Zhang, Xuanliang, et al.
Published: (2024)

RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
by: Jiang, Jinhao, et al.
Published: (2024)

Improving the Downstream Performance of Mixture-of-Experts Transformers via Weak Vanilla Transformers
by: Lu, Xin, et al.
Published: (2024)

Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey
by: Yang, Hao, et al.
Published: (2024)

RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals
by: Zhang, Xuanliang, et al.
Published: (2025)