Cover Image

Scalable Complexity Control Facilitates Reasoning Ability of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hang, Liangkai, Yao, Junjie, Bai, Zhiwei, Chen, Tianyi, Chen, Yang, Diao, Rongjie, Li, Hezhou, Lin, Pengxiao, Wang, Zhiwei, Xu, Cheng, Zhang, Zhongwang, Zhou, Zhangchen, Li, Zhiyu, Lin, Zehao, Chen, Kai, Xiong, Feiyu, Zhang, Yaoyu, E, Weinan, Yang, Hongkang, Xu, Zhi-Qin John
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
by: Zhang, Zhongwang, et al.
Published: (2025)

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
by: Zhang, Zhongwang, et al.
Published: (2024)

Adaptive Preconditioners Trigger Loss Spikes in Adam
by: Bai, Zhiwei, et al.
Published: (2025)

Anchor function: a type of benchmark functions for studying language models
by: Zhang, Zhongwang, et al.
Published: (2024)

Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data
by: Chen, Tianyi, et al.
Published: (2025)

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
by: Zhang, Yaoyu, et al.
Published: (2024)

Reasoning Bias of Next Token Prediction Training
by: Lin, Pengxiao, et al.
Published: (2025)

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
by: Wang, Zhiwei, et al.
Published: (2024)

Solving multiscale dynamical systems by deep learning
by: Yao, Junjie, et al.
Published: (2024)

A rationale from frequency perspective for grokking in training neural network
by: Zhou, Zhangchen, et al.
Published: (2024)

An overview of condensation phenomenon in deep learning
by: Xu, Zhi-Qin John, et al.
Published: (2025)

Loss Jump During Loss Switch in Solving PDEs with Neural Networks
by: Wang, Zhiwei, et al.
Published: (2024)

Generalization Error of GAN from the Discriminator's Perspective
by: Yang, Hongkang, et al.
Published: (2021)

Identity Bridge: Enabling Implicit Reasoning via Shared Latent Memory
by: Lin, Pengxiao, et al.
Published: (2025)

Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
by: Bai, Zhiwei, et al.
Published: (2024)

Disentangle Sample Size and Initialization Effect on Perfect Generalization for Single-Neuron Target
by: Zhao, Jiajie, et al.
Published: (2024)

On the extreme points of sets of absolulely separable and PPT states
by: Song, Zhiwei, et al.
Published: (2024)

Spectral characterizations of entanglement witnesses
by: Song, Zhiwei, et al.
Published: (2025)

A counterexample to the strong spin alignment conjecture
by: Song, Zhiwei, et al.
Published: (2026)

Life’s Essential 8 and Mortality Risk in Cardiovascular Disease: Results From a Nationwide Population Survey
by: Yang Zhang, et al.
Published: (2025)

FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion
by: Ruan, Jiacheng, et al.
Published: (2024)

Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
by: Bai, Zhiwei, et al.
Published: (2022)

$\text{Memory}^3$: Language Modeling with Explicit Memory
by: Yang, Hongkang, et al.
Published: (2024)

An Analysis for Reasoning Bias of Language Models with Small Initialization
by: Yao, Junjie, et al.
Published: (2025)

CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
by: Lin, Shen, et al.
Published: (2026)

Focus and Dilution: The Multi-stage Learning Process of Attention
by: Chen, Zheng-An, et al.
Published: (2026)

Perceptual Group Tokenizer: Building Perception with Iterative Grouping
by: Deng, Zhiwei, et al.
Published: (2023)

NGENT: Next-Generation AI Agents Must Integrate Multi-Domain Abilities to Achieve Artificial General Intelligence
by: Li, Zhicong, et al.
Published: (2025)

Mechanically Interlocked Solid‐Solid Bicontinuous Phase Epoxy/Water‐In‐Salt Hydrogel Structural Electrolyte for Zinc‐Lithium Hybrid Structural Batteries
by: Feihong Chen, et al.
Published: (2025)

Postharvet Jasmine Test Data
by: Chen, Zhiwei
Published: (2025)

Robustness Inspired Graph Backdoor Defense
by: Zhang, Zhiwei, et al.
Published: (2024)

Input gradient annealing neural network for solving low-temperature Fokker-Planck equations
by: Hang, Liangkai, et al.
Published: (2024)

Constructing three-qubit unitary gates in terms of Schmidt rank and CNOT gates
by: Song, Zhiwei, et al.
Published: (2020)

Mutually-orthogonal unitary and orthogonal matrices
by: Song, Zhiwei, et al.
Published: (2023)

Multipartite entangling power by von Neumann entropy
by: Qiu, Xinyu, et al.
Published: (2024)

Extreme points of absolutely PPT states with exactly three distinct eigenvalues
by: Wang, Nalan, et al.
Published: (2026)

Multi-Task Anti-Causal Learning for Reconstructing Urban Events from Residents' Reports
by: Zhou, Liangkai, et al.
Published: (2026)

DAA*: Deep Angular A Star for Image-based Path Planning
by: Xu, Zhiwei
Published: (2025)

MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
by: Li, Zhiyu, et al.
Published: (2025)

Reconstruction of multiple strings of constant weight from prefix-suffix compositions
by: Yang, Yaoyu, et al.
Published: (2024)