Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning

TL;DR

Table-Critic introduces a multi-agent framework that enhances table reasoning in large language models by enabling collaborative error detection, critique, and iterative refinement, significantly improving accuracy and robustness.

Contribution

The paper presents a novel multi-agent system with specialized roles and a self-evolving template tree to improve error correction and reasoning consistency in table-based tasks.

Findings

Achieves higher accuracy than existing methods.

Reduces error propagation in multi-step reasoning.

Maintains computational efficiency.

Abstract

Despite the remarkable capabilities of large language models (LLMs) in various reasoning tasks, they still struggle with table reasoning tasks, particularly in maintaining consistency throughout multi-step reasoning processes. While existing approaches have explored various decomposition strategies, they often lack effective mechanisms to identify and correct errors in intermediate reasoning steps, leading to cascading error propagation. To address these issues, we propose Table-Critic, a novel multi-agent framework that facilitates collaborative criticism and iterative refinement of the reasoning process until convergence to correct solutions. Our framework consists of four specialized agents: a Judge for error identification, a Critic for comprehensive critiques, a Refiner for process improvement, and a Curator for pattern distillation. To effectively deal with diverse and unpredictable error types, we introduce a self-evolving template tree that systematically accumulates critique knowledge through experience-driven learning and guides future reflections. Extensive experiments have demonstrated that Table-Critic achieves substantial improvements over existing methods, achieving superior accuracy and error correction rates while maintaining computational efficiency and lower solution degradation rate.