PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion

TL;DR

PanelTR introduces a multi-agent scientific discussion framework using LLMs for zero-shot table reasoning, outperforming baseline models without relying on data augmentation or training.

Contribution

The paper presents a novel structured scientific approach with agent scientists for zero-shot table reasoning, avoiding data augmentation and parametric optimization.

Findings

Outperforms vanilla LLMs on four benchmarks

Rivals fully supervised models without training data

Demonstrates effective semantic transfer in zero-shot setting

Abstract

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.