PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909910094053376 |
|---|---|
| author | Ma, Yiran Rex |
| author_facet | Ma, Yiran Rex |
| contents | Table reasoning, including tabular QA and fact verification, often depends on annotated data or complex data augmentation, limiting flexibility and generalization. LLMs, despite their versatility, often underperform compared to simple supervised models. To approach these issues, we introduce PanelTR, a framework utilizing LLM agent scientists for robust table reasoning through a structured scientific approach. PanelTR's workflow involves agent scientists conducting individual investigations, engaging in self-review, and participating in collaborative peer-review discussions. This process, driven by five scientist personas, enables semantic-level transfer without relying on data augmentation or parametric optimization. Experiments across four benchmarks show that PanelTR outperforms vanilla LLMs and rivals fully supervised models, all while remaining independent of training data. Our findings indicate that structured scientific methodology can effectively handle complex tasks beyond table reasoning with flexible semantic understanding in a zero-shot context. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06110 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion Ma, Yiran Rex Artificial Intelligence Multiagent Systems Table reasoning, including tabular QA and fact verification, often depends on annotated data or complex data augmentation, limiting flexibility and generalization. LLMs, despite their versatility, often underperform compared to simple supervised models. To approach these issues, we introduce PanelTR, a framework utilizing LLM agent scientists for robust table reasoning through a structured scientific approach. PanelTR's workflow involves agent scientists conducting individual investigations, engaging in self-review, and participating in collaborative peer-review discussions. This process, driven by five scientist personas, enables semantic-level transfer without relying on data augmentation or parametric optimization. Experiments across four benchmarks show that PanelTR outperforms vanilla LLMs and rivals fully supervised models, all while remaining independent of training data. Our findings indicate that structured scientific methodology can effectively handle complex tasks beyond table reasoning with flexible semantic understanding in a zero-shot context. |
| title | PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2508.06110 |