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

arXiv: https://arxiv.org/abs/2601.14599 · HTML: https://mlsanity.com/paper/2601.14599/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [2 OLMo 2 Furious](https://mlsanity.com/paper/2501.00656/) (2024)
- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization](https://mlsanity.com/paper/2501.03262/) (2025)
- [Spurious Rewards: Rethinking Training Signals in RLVR](https://mlsanity.com/paper/2506.10947/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling](https://mlsanity.com/paper/2506.20512/) (2025)
- [The Art of Scaling Reinforcement Learning Compute for LLMs](https://mlsanity.com/paper/2510.13786/) (2025)
- [All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning](https://mlsanity.com/paper/2503.01067/) (2025)
- [Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration](https://mlsanity.com/paper/2508.13755/) (2025)
- [Sharp Analysis for KL-Regularized Contextual Bandits and RLHF](https://mlsanity.com/paper/2411.04625/) (2024)
- [Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward](https://mlsanity.com/paper/2512.16912/) (2025)
- [Scaling Law for Language Models Training Considering Batch Size](https://mlsanity.com/paper/2412.01505/) (2024)
- [GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy](https://mlsanity.com/paper/2508.04349/) (2025)
- [Hard Examples Are All You Need: Maximizing GRPO Post-Training Under Annotation Budgets](https://mlsanity.com/paper/2508.14094/) (2025)
- [RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs](https://mlsanity.com/paper/2508.16546/) (2025)
- [Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning](https://mlsanity.com/paper/2509.22611/) (2025)
- [Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO](https://mlsanity.com/paper/2509.24494/) (2025)
- [Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits](https://mlsanity.com/paper/2505.20268/) (2025)

## Abstract (arXiv)

A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive. Reflecting on this situation, two fundamental questions still lack a clear understanding: 1) what is the role of each optimizing choice? 2) which ones are the bottlenecks? This paper aims to shed light on them, and it faces the challenge of several entangled confounding factors in the fine-tuning process. To tackle this challenge, we propose a bottom-up experiment pipeline. The bottom layer is composed of a minimalist configuration: one training data, one rollout per round and the reward directly serve as the learning signal without advantage function design. This minimalist configuration connects to multi-armed bandit learning with extremely large discrete action space, which offers theories to corroborate the experiment findings. The up procedure of the experiment pipeline expanding the minimalist configuration layer by layer, examining the role of each design choice. Experimental results on three LLMs and two reasoning datasets not only reveal new understanding of the design choice but also yield essential insights to shape the area.