TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912788912275456 |
|---|---|
| author | Yang, Saisai Huang, Qingyi Yuan, Jing Zha, Liangyu Tang, Kai Yang, Yuhang Wang, Ning Wei, Yucheng Li, Liyao Ye, Wentao Chen, Hao Zhang, Tao Zhou, Junlin Wang, Haobo Chen, Gang Zhao, Junbo |
| author_facet | Yang, Saisai Huang, Qingyi Yuan, Jing Zha, Liangyu Tang, Kai Yang, Yuhang Wang, Ning Wei, Yucheng Li, Liyao Ye, Wentao Chen, Hao Zhang, Tao Zhou, Junlin Wang, Haobo Chen, Gang Zhao, Junbo |
| contents | Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significantly improved natural language interaction with such structured data, they often fall short in handling the complex, multi-step reasoning and robust code execution required for real-world table tasks. Reinforcement Learning (RL) offers a promising avenue to enhance these capabilities, yet its application in the tabular domain faces three critical hurdles: the scarcity of high-quality agentic trajectories with closed-loop code execution and environment feedback on diverse table structures, the extreme heterogeneity of feedback signals ranging from rigid SQL execution to open-ended data interpretation, and the risk of catastrophic forgetting of general knowledge during vertical specialization. To overcome these challenges and unlock advanced reasoning on complex tables, we introduce \textbf{TableGPT-R1}, a specialized tabular model built on a systematic RL framework. Our approach integrates a comprehensive data engineering pipeline that synthesizes difficulty-stratified agentic trajectories for both supervised alignment and RL rollouts, a task-adaptive reward system that combines rule-based verification with a criteria-injected reward model and incorporates process-level step reward shaping with behavioral regularization, and a multi-stage training framework that progressively stabilizes reasoning before specializing in table-specific tasks. Extensive evaluations demonstrate that TableGPT-R1 achieves state-of-the-art performance on authoritative benchmarks, significantly outperforming baseline models while retaining robust general capabilities. Our model is available at https://huggingface.co/tablegpt/TableGPT-R1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20312 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning Yang, Saisai Huang, Qingyi Yuan, Jing Zha, Liangyu Tang, Kai Yang, Yuhang Wang, Ning Wei, Yucheng Li, Liyao Ye, Wentao Chen, Hao Zhang, Tao Zhou, Junlin Wang, Haobo Chen, Gang Zhao, Junbo Machine Learning Artificial Intelligence Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significantly improved natural language interaction with such structured data, they often fall short in handling the complex, multi-step reasoning and robust code execution required for real-world table tasks. Reinforcement Learning (RL) offers a promising avenue to enhance these capabilities, yet its application in the tabular domain faces three critical hurdles: the scarcity of high-quality agentic trajectories with closed-loop code execution and environment feedback on diverse table structures, the extreme heterogeneity of feedback signals ranging from rigid SQL execution to open-ended data interpretation, and the risk of catastrophic forgetting of general knowledge during vertical specialization. To overcome these challenges and unlock advanced reasoning on complex tables, we introduce \textbf{TableGPT-R1}, a specialized tabular model built on a systematic RL framework. Our approach integrates a comprehensive data engineering pipeline that synthesizes difficulty-stratified agentic trajectories for both supervised alignment and RL rollouts, a task-adaptive reward system that combines rule-based verification with a criteria-injected reward model and incorporates process-level step reward shaping with behavioral regularization, and a multi-stage training framework that progressively stabilizes reasoning before specializing in table-specific tasks. Extensive evaluations demonstrate that TableGPT-R1 achieves state-of-the-art performance on authoritative benchmarks, significantly outperforming baseline models while retaining robust general capabilities. Our model is available at https://huggingface.co/tablegpt/TableGPT-R1. |
| title | TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.20312 |