Cover Image

Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rao, Jun, Liu, Xuebo, Deng, Hexuan, Lin, Zepeng, Yu, Zixiong, Wei, Jiansheng, Meng, Xiaojun, Zhang, Min
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

MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis
by: Yu, Zixiong, et al.
Published: (2026)

REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning
by: Deng, Hexuan, et al.
Published: (2025)

AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs
by: Ke, Xiaopeng, et al.
Published: (2025)

RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
by: Yuan, Bo, et al.
Published: (2026)

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training
by: Rao, Jun, et al.
Published: (2025)

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
by: Deng, Hexuan, et al.
Published: (2024)

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
by: Nie, Shuo, et al.
Published: (2026)

NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
by: Deng, Hexuan, et al.
Published: (2024)

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models
by: Rao, Jun, et al.
Published: (2025)

Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models
by: Rao, Jun, et al.
Published: (2024)

CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions
by: Rao, Jun, et al.
Published: (2024)

AdaptGrad: Adaptive Sampling to Reduce Noise
by: Zhou, Linjiang, et al.
Published: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
by: Liang, Jianxin, et al.
Published: (2025)

CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory
by: Zhao, Haokun, et al.
Published: (2025)

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning
by: Deng, Jie, et al.
Published: (2026)

SGIC: A Self-Guided Iterative Calibration Framework for RAG
by: Chen, Guanhua, et al.
Published: (2025)

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning
by: Kim, Junseok, et al.
Published: (2026)

CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
by: Deng, Hexuan, et al.
Published: (2026)

Efficient Mathematical Reasoning Models via Dynamic Pruning and Knowledge Distillation
by: Yu, Fengming, et al.
Published: (2025)

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
by: Xu, Huimin, et al.
Published: (2025)

Machine Learning Potential Powered Insights into the Mechanical Stability of Amorphous Li-Si Alloys
by: Wei, Zixiong, et al.
Published: (2024)

History-Guided Iterative Visual Reasoning with Self-Correction
by: Yang, Xinglong, et al.
Published: (2026)

Persistent Cross-Attempt State Optimization for Repository-Level Code Generation
by: Pan, Ruwei, et al.
Published: (2026)

3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
by: Ma, Xinyu, et al.
Published: (2024)

Controllable Mathematical Reasoning via Self-Optimizing Thought Vectors
by: LI, Xuying
Published: (2025)

TasTe: Teaching Large Language Models to Translate through Self-Reflection
by: Wang, Yutong, et al.
Published: (2024)

Relaxation Dynamics in Persistent Epithelial Tissues
by: Li, Meng-Yuan, et al.
Published: (2024)

A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data
by: Li, Wenqiang, et al.
Published: (2023)

CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
by: Wang, Zhuo, et al.
Published: (2026)

SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
by: Liu, Liangxin, et al.
Published: (2024)

Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing
by: Lou, Meng, et al.
Published: (2026)

MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning
by: Lin, Yunze
Published: (2025)

A Probabilistic Approach for Demand-Aware Ride-Sharing Optimization
by: Lin, Qiulin, et al.
Published: (2019)

Iterative Reasoning Preference Optimization
by: Pang, Richard Yuanzhe, et al.
Published: (2024)

PureSample: Neural Materials Learned by Sampling Microgeometry
by: Li, Zixuan, et al.
Published: (2025)

Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
by: Li, Yang, et al.
Published: (2025)

Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning
by: Mu, Yongyu, et al.
Published: (2026)

Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
by: Wan, Guangya, et al.
Published: (2024)

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
by: Song, Mingyang, et al.
Published: (2026)

FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
by: Ding, Yuyang, et al.
Published: (2025)