Cover Image

Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Zhichao, Fan, Zhaoxin, Li, Gen, Hu, Yuanze, Wang, Xinyu, Qiu, Ye, Wang, Xin, Sun, Yifan, Wu, Wenjun
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
by: Hu, Yuanze, et al.
Published: (2025)

State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading
by: Hu, Yuanze, et al.
Published: (2026)

The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
by: Qin, Zixuan, et al.
Published: (2025)

EMG-UP: Unsupervised Personalization in Cross-User EMG Gesture Recognition
by: Wang, Nana, et al.
Published: (2025)

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization
by: Lan, Yuqin, et al.
Published: (2026)

Bribery Can Get Harder in Structured Multiwinner Approval Election
by: Kusek, Bartosz, et al.
Published: (2022)

Scaling Laws for Predicting Downstream Performance in LLMs
by: Chen, Yangyi, et al.
Published: (2024)

Tackling the Inherent Difficulty of Noise Filtering in RAG
by: Liu, Jingyu, et al.
Published: (2026)

RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks
by: Duan, Shiying, et al.
Published: (2025)

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
by: Dai, Yanqi, et al.
Published: (2026)

Burger: Robust Graph Denoising-augmentation Fusion and Multi-semantic Modeling in Social Recommendation
by: Lan, Yuqin, et al.
Published: (2025)

Can Language Models Discover Scaling Laws?
by: Lin, Haowei, et al.
Published: (2025)

TaskSense: Cognitive Chain Modeling and Difficulty Estimation for GUI Tasks
by: Yin, Yiwen, et al.
Published: (2025)

Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs
by: Xu, Zifei, et al.
Published: (2024)

Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks
by: Gong, Chang, et al.
Published: (2025)

A Deeper Dive into the Irreversibility of PolyProtect: Making Protected Face Templates Harder to Invert
by: Hahn, Vedrana Krivokuća, et al.
Published: (2026)

Can the gravitational wave background feel wiggles in spacetime?
by: Ye, Gen, et al.
Published: (2023)

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction
by: Li, Ming, et al.
Published: (2025)

Brain Structural Connectivity and Morphological Awareness Mediate the Association Between Home Literacy Environment and Reading Outcomes in Children With Family History of Reading Difficulties
by: Xianglin Zhang, et al.
Published: (2025)

Considerations on the Study of Predictive Factors for sBEA‐ESD Technical Difficulty
by: Wenjun Jiang
Published: (2026)

Reasoning Gets Harder for LLMs Inside A Dialogue
by: Kartáč, Ivan, et al.
Published: (2026)

HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
by: Chen, Boshui, et al.
Published: (2026)

Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
by: He, Xin, et al.
Published: (2025)

TRTM: Template-based Reconstruction and Target-oriented Manipulation of Crumpled Cloths
by: Wang, Wenbo, et al.
Published: (2023)

Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
by: Li, Yuanze, et al.
Published: (2024)

Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks
by: Buszydlik, Aleksander, et al.
Published: (2023)

Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
by: Qu, Yun, et al.
Published: (2025)

Power-Law Scaling in the Classification Performance of Small-Scale Spiking Neural Networks
by: Zhang, Zhengdi, et al.
Published: (2026)

Stability Conditions and Harder-Narasimhan Filtrations for Triangulated Categories
by: Gao, Wenyu, et al.
Published: (2025)

Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?
by: Yang, Zhe, et al.
Published: (2024)

Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check
by: Lourie, Nicholas, et al.
Published: (2025)

Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
by: Wang, Zhaoxin, et al.
Published: (2025)

Relative Scaling Laws for LLMs
by: Held, William, et al.
Published: (2025)

EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
by: Fan, Zhaoxin, et al.
Published: (2026)

Predicting Task Performance with Context-aware Scaling Laws
by: Montgomery, Kyle, et al.
Published: (2025)

Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
by: Yang, Bangji, et al.
Published: (2026)

Lyapunov Probes for Hallucination Detection in Large Foundation Models
by: Luan, Bozhi, et al.
Published: (2026)

TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs
by: Wang, Ziyi, et al.
Published: (2026)

Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning
by: Golowich, Noah, et al.
Published: (2024)

Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
by: Li, Mingzhuo, et al.
Published: (2025)