Cover Image

Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Minwu, Shrestha, Anubhav, Shrestha, Safal, Nepal, Aadim, Ross, Keith
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

Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings
by: Shrestha, Safal, et al.
Published: (2025)

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
by: Shrestha, Safal, et al.
Published: (2026)

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning
by: Kim, Minwu, et al.
Published: (2026)

Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges
by: Shrestha, Safal, et al.
Published: (2025)

Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training
by: Nepal, Aadim, et al.
Published: (2025)

Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search
by: Shrestha, Manil, et al.
Published: (2025)

Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR
by: Sharma, Rishikesh Kumar, et al.
Published: (2026)

Conformal Prediction for Risk-Controlled Medical Entity Extraction Across Clinical Domains
by: Shrestha, Manil, et al.
Published: (2026)

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
by: Huan, Maggie, et al.
Published: (2025)

Towards Nepali-language LLMs: Efficient GPT training with a Nepali BPE tokenizer
by: Shrestha, Adarsha, et al.
Published: (2025)

A Survey on LLM-Assisted Clinical Trial Recruitment
by: Ghosh, Shrestha, et al.
Published: (2025)

Visual Grounding Methods for VQA are Working for the Wrong Reasons!
by: Shrestha, Robik, et al.
Published: (2020)

ALIGN: Word Association Learning for Cultural Alignment in Large Language Models
by: Liu, Chunhua, et al.
Published: (2025)

Distilling Mathematical Reasoning Capabilities into Small Language Models
by: Zhu, Xunyu, et al.
Published: (2024)

Enabling LLM Knowledge Analysis via Extensive Materialization
by: Hu, Yujia, et al.
Published: (2024)

WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
by: Zhuang, Yuchen, et al.
Published: (2025)

Dual-Head Reasoning Distillation: Improving Classifier Accuracy with Train-Time-Only Reasoning
by: Xu, Jillian, et al.
Published: (2025)

Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge
by: Ghosh, Shrestha, et al.
Published: (2025)

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning
by: Hu, Bokai, et al.
Published: (2024)

ReAD: Reinforcement-Guided Capability Distillation for Large Language Models
by: Cheng, Xueqi, et al.
Published: (2026)

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
by: Wu, Zhaofeng, et al.
Published: (2023)

Difficulty Estimation and Simplification of French Text Using LLMs
by: Jamet, Henri, et al.
Published: (2024)

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

Improving Mathematical Reasoning Capabilities of Small Language Models via Feedback-Driven Distillation
by: Zhu, Xunyu, et al.
Published: (2024)

Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean
by: Park, Chanwoo, et al.
Published: (2025)

Skill-Conditioned Gated Self-Distillation for LLM Reasoning
by: Huang, Jiazhen, et al.
Published: (2026)

Let's Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM's Math Capability
by: Wang, Ruida, et al.
Published: (2025)

Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation
by: Padarha, Shreyansh
Published: (2025)

Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
by: Xiao, Yilin, et al.
Published: (2025)

Token-Driven GammaTune: Adaptive Calibration for Enhanced Speculative Decoding
by: Gautam, Aayush, et al.
Published: (2025)

Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans
by: Kwon, Deuksin, et al.
Published: (2025)

GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
by: Luo, Zihan, et al.
Published: (2024)

Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
by: Xie, Tian, et al.
Published: (2025)

LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News Detection
by: Zhou, Weilin, et al.
Published: (2026)

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
by: Jiao, Rui, et al.
Published: (2025)

R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
by: Weyssow, Martin, et al.
Published: (2025)

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch
by: Ding, Yuyang, et al.
Published: (2024)

Steamroller Problems: An Evaluation of LLM Reasoning Capability with Automated Theorem Prover Strategies
by: McGinness, Lachlan, et al.
Published: (2024)

Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
by: Sun, Yiliu, et al.
Published: (2025)

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
by: Zhang, Kongcheng, et al.
Published: (2025)