Cover Image

Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Xiao, Xie, Hong, Tan, Tao, Lian, Defu, Han, Jianyu
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective
by: Xie, Hong, et al.
Published: (2026)

LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs
by: Hu, Xiao, et al.
Published: (2025)

Multi-agent Multi-armed Bandits with Stochastic Sharable Arm Capacities
by: Xie, Hong, et al.
Published: (2024)

Learning from models beyond fine-tuning
by: Zheng, Hongling, et al.
Published: (2023)

Deceptive Exploration in Multi-armed Bandits
by: Vurankaya, I. Arda, et al.
Published: (2025)

Causally Abstracted Multi-armed Bandits
by: Zennaro, Fabio Massimo, et al.
Published: (2024)

Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users
by: Yang, Hantao, et al.
Published: (2024)

Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
by: Kim, Minseon, et al.
Published: (2025)

Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization
by: Zhao, Yunfan, et al.
Published: (2023)

Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits
by: Jeong, Woojin, et al.
Published: (2024)

Rethinking harmless refusals when fine-tuning foundation models
by: Pop, Florin, et al.
Published: (2024)

Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing
by: Xie, Hong, et al.
Published: (2025)

Networked Restless Multi-Arm Bandits with Reinforcement Learning
by: Zhang, Hanmo, et al.
Published: (2025)

Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs
by: Chen, Jack, et al.
Published: (2025)

Combinatorial Multi-armed Bandits: Arm Selection via Group Testing
by: Mukherjee, Arpan, et al.
Published: (2024)

Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
by: Xiong, Guojun, et al.
Published: (2024)

LLMs Are In-Context Bandit Reinforcement Learners
by: Monea, Giovanni, et al.
Published: (2024)

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
by: Duan, Tianyang, et al.
Published: (2025)

Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values
by: Sharma, Shradha, et al.
Published: (2026)

M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
by: Chen, Jianlv, et al.
Published: (2024)

Adaptive Multi-Agent Deep Reinforcement Learning for Timely Healthcare Interventions
by: Shaik, Thanveer, et al.
Published: (2023)

Uncertainty quantification in fine-tuned LLMs using LoRA ensembles
by: Balabanov, Oleksandr, et al.
Published: (2024)

Comparing Exploration-Exploitation Strategies of LLMs and Humans: Insights from Standard Multi-armed Bandit Experiments
by: Zhang, Ziyuan, et al.
Published: (2025)

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
by: Lu, Xiaodong, et al.
Published: (2026)

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
by: Kong, Deyang, et al.
Published: (2025)

Foundations and Frontiers of Graph Learning Theory
by: Huang, Yu, et al.
Published: (2024)

Rethinking Plasticity in Deep Reinforcement Learning
by: He, Zhiqiang
Published: (2026)

Rethinking the Foundations for Continual Reinforcement Learning
by: Elelimy, Esraa, et al.
Published: (2025)

An Electrocardiogram Multi-task Benchmark with Comprehensive Evaluations and Insightful Findings
by: Xu, Yuhao, et al.
Published: (2025)

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
by: Ji, Qirui, et al.
Published: (2023)

KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
by: Ran, Dezhi, et al.
Published: (2025)

Empirical influence functions to understand the logic of fine-tuning
by: Matelsky, Jordan K., et al.
Published: (2024)

Efficient Machine Unlearning via Influence Approximation
by: Liu, Jiawei, et al.
Published: (2025)

FLoRA: Fused forward-backward adapters for parameter efficient fine-tuning and reducing inference-time latencies of LLMs
by: Gowda, Dhananjaya, et al.
Published: (2025)

When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
by: Ye, Wen, et al.
Published: (2025)

Protein-Conditioned Multi-Objective Reinforcement Learning for Full-Length mRNA Design
by: Shao, Zixi, et al.
Published: (2026)

Fine-tuning Timeseries Predictors Using Reinforcement Learning
by: Cazaux, Hugo, et al.
Published: (2026)

TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
by: Li, Yuanpeng, et al.
Published: (2026)

EnECG: Efficient Ensemble Learning for Electrocardiogram Multi-task Foundation Model
by: Xu, Yuhao, et al.
Published: (2025)

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning
by: Wu, Chenyuan, et al.
Published: (2024)