---
title: "Rui Lu — papers of 2025 — 3 papers, the most cited first"
description: "Rui Lu — papers of 2025: 3 papers on Elamur Research, the most cited first — what each work is about in our own words."
canonical: "https://research.elamur.ai/free/en/authors/rui-lu/year/2025/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/rui-lu/year/2025/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Rui Lu](https://md.research.elamur.ai/free/en/authors/rui-lu/) / 2025

# Rui Lu — papers of 2025 — 3 papers, the most cited first

3 papers · [all years of Rui Lu](https://md.research.elamur.ai/free/en/authors/rui-lu/#years)

- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? arXiv:2504.13837 · NeurIPS 2025 Oral; ICML 2025 AI4MATH workshop best paper](https://md.research.elamur.ai/free/en/papers/yue-2025-reinforcement-learning-really-incentivize-reasoning/) — Yang Yue, Zhiqi Chen, Rui Lu, et al. · 2025 · 216 citations

**[Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://md.research.elamur.ai/free/en/papers/wang-2025-80-20-rule-high-entropy/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Shenzhi Wang, Le Yu, Chang Gao, et al.*2025 · 152 citations*

**[TreeRL: LLM Reinforcement Learning with On-Policy Tree Search](https://md.research.elamur.ai/free/en/papers/hou-2025-treerl-llm-reinforcement-learning-policy/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zhenyu Hou, Ziniu Hu, Yujiang Li, et al.*2025 · 26 citations*