Cover Image

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Yiju, Hu, Tianyi, Sun, Zexu, Lin, Yankai
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
by: Yang, Wenkai, et al.
Published: (2025)

Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency
by: Huang, Rapheal, et al.
Published: (2025)

Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning
by: Wu, Bohao, et al.
Published: (2025)

HIPO: Instruction Hierarchy via Constrained Reinforcement Learning
by: Chen, Keru, et al.
Published: (2026)

LIMR: Less is More for RL Scaling
by: Li, Xuefeng, et al.
Published: (2025)

Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation
by: Zheng, Yilun, et al.
Published: (2025)

Less is More: Improving LLM Alignment via Preference Data Selection
by: Deng, Xun, et al.
Published: (2025)

Supernova: Achieving More with Less in Transformer Architectures
by: Tanase, Andrei-Valentin, et al.
Published: (2025)

Less is More: Local Intrinsic Dimensions of Contextual Language Models
by: Ruppik, Benjamin Matthias, et al.
Published: (2025)

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
by: Suvarna, Ashima, et al.
Published: (2026)

Less is More for Improving Automatic Evaluation of Factual Consistency
by: Wang, Tong, et al.
Published: (2024)

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM
by: Liu, Yibai, et al.
Published: (2025)

When Less is Enough: Efficient Inference via Collaborative Reasoning
by: Chen, Yilei, et al.
Published: (2026)

When More is Less: Understanding Chain-of-Thought Length in LLMs
by: Wu, Yuyang, et al.
Published: (2025)

Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation
by: Riaz, Haris, et al.
Published: (2025)

LoRA Learns Less and Forgets Less
by: Biderman, Dan, et al.
Published: (2024)

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
by: Li, Ming, et al.
Published: (2025)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
by: Deng, Wenhao, et al.
Published: (2025)

Should We Attend More or Less? Modulating Attention for Fairness
by: Zayed, Abdelrahman, et al.
Published: (2023)

Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs
by: Zhang, Yifei, et al.
Published: (2024)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
by: Ma, Zhengzhao, et al.
Published: (2026)

Towards More Accurate US Presidential Election via Multi-step Reasoning with Large Language Models
by: Yu, Chenxiao, et al.
Published: (2024)

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets
by: Wei, Lai, et al.
Published: (2023)

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
by: Liu, Bo, et al.
Published: (2025)

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
by: DeepSeek-AI, et al.
Published: (2025)

Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
by: Hathidara, Ashutosh, et al.
Published: (2025)

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
by: Xi, Zhiheng, et al.
Published: (2024)

From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
by: Jiang, Xitai, et al.
Published: (2026)

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning
by: Liu, Shih-Yang, et al.
Published: (2025)

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
by: You, Haoran, et al.
Published: (2024)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
by: Fan, Chenrui, et al.
Published: (2025)

Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
by: Xu, Ran, et al.
Published: (2025)

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
by: Luo, Haipeng, et al.
Published: (2023)

Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
by: Zou, Junyi
Published: (2026)

More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models
by: Wang, Xiao
Published: (2026)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
by: Zhang, Kaiyi, et al.
Published: (2025)

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
by: Hu, Junhao, et al.
Published: (2026)

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
by: Yang, Wenkai, et al.
Published: (2026)

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
by: Xu, Wanghan, et al.
Published: (2026)

Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
by: Zhang, Kongcheng, et al.
Published: (2025)