Cover Image

How Far Are We from Optimal Reasoning Efficiency?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Jiaxuan, Yan, Shu, Tan, Qixin, Yang, Lu, Xu, Shusheng, Fu, Wei, Mei, Zhiyu, Lyu, Kaifeng, Wu, Yi
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

On Designing Effective RL Reward at Training Time for LLM Reasoning
by: Gao, Jiaxuan, et al.
Published: (2024)

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
by: Gao, Jiaxuan, et al.
Published: (2025)

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
by: Xu, Shusheng, et al.
Published: (2024)

LLMs for Relational Reasoning: How Far are We?
by: Li, Zhiming, et al.
Published: (2024)

How Far Are We From AGI: Are LLMs All We Need?
by: Feng, Tao, et al.
Published: (2024)

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
by: Gao, Jiaxuan, et al.
Published: (2026)

PixelWorld: How Far Are We from Perceiving Everything as Pixels?
by: Lyu, Zhiheng, et al.
Published: (2025)

Reasoning Runtime Behavior of a Program with LLM: How Far Are We?
by: Chen, Junkai, et al.
Published: (2024)

How Far Are We from Intelligent Visual Deductive Reasoning?
by: Zhang, Yizhe, et al.
Published: (2024)

MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?
by: Yong, Xixian, et al.
Published: (2025)

How Far Are We? Systematic Evaluation of LLMs vs. Human Experts in Mathematical Contest in Modeling
by: Liu, Yuhang, et al.
Published: (2026)

Vulnerability Detection with Code Language Models: How Far Are We?
by: Ding, Yangruibo, et al.
Published: (2024)

How Far Are We from Genuinely Useful Deep Research Agents?
by: Zhang, Dingling, et al.
Published: (2025)

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
by: Fu, Wei, et al.
Published: (2025)

Model Editing for LLMs4Code: How Far are We?
by: Li, Xiaopeng, et al.
Published: (2024)

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
by: Lu, Yi, et al.
Published: (2025)

LLM Compression: How Far Can We Go in Balancing Size and Performance?
by: Sk, Sahil, et al.
Published: (2025)

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
by: Huang, Jen-tse, et al.
Published: (2024)

Financial Named Entity Recognition: How Far Can LLM Go?
by: Lu, Yi-Te, et al.
Published: (2025)

How Far Can We Extract Diverse Perspectives from Large Language Models?
by: Hayati, Shirley Anugrah, et al.
Published: (2023)

AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
by: Zhang, Jiarui, et al.
Published: (2026)

How Far Are We from Generating Missing Modalities with Foundation Models?
by: Ke, Guanzhou, et al.
Published: (2025)

How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning
by: Yang, Luyu, et al.
Published: (2026)

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
by: Li, Jiazheng, et al.
Published: (2025)

Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?
by: Li, Bangzheng, et al.
Published: (2023)

PACE: A Pragmatic Agent for Enhancing Communication Efficiency Using Large Language Models
by: Li, Jiaxuan, et al.
Published: (2024)

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
by: Wu, Xingyu, et al.
Published: (2025)

How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation
by: Xiao, Yang, et al.
Published: (2023)

The Power of Power Law: Asymmetry Enables Compositional Reasoning
by: Wang, Zixuan, et al.
Published: (2026)

Mind with Eyes: from Language Reasoning to Multimodal Reasoning
by: Lin, Zhiyu, et al.
Published: (2025)

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs
by: Yang, Shu, et al.
Published: (2025)

How Far Can 100 Samples Go? Unlocking Overall Zero-Shot Multilingual Translation via Tiny Multi-Parallel Data
by: Wu, Di, et al.
Published: (2024)

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
by: Lin, Zhengkai, et al.
Published: (2024)

Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
by: Xin, Yuan, et al.
Published: (2025)

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
by: Huang, Heyan, et al.
Published: (2024)

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
by: Wang, Haozhe, et al.
Published: (2025)

ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation
by: Mei, Zhiyu, et al.
Published: (2024)

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
by: Mei, Zhiyu, et al.
Published: (2023)

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
by: Zhang, Zhexin, et al.
Published: (2025)

How Far Can Unsupervised RLVR Scale LLM Training?
by: He, Bingxiang, et al.
Published: (2026)