Xiaoran Fan

发表论文 40 篇 · 总被引 3101 次 · h-index 14

代表论文

• The rise and potential of large language model based agents: a survey (2025 · Science China Information Sciences · 被引 433)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback (2024 · arXiv.org · 被引 97)
• Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination (2025 · AAAI Conference on Artificial Intelligence · 被引 81)
• Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective (2025 · 被引 14)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments (2025 · Annual Meeting of the Association for Computational Linguistics · 被引 14)
• Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 13)